{ "$schema": "https://models.viglet.org/catalog.schema.json", "version": 1, "lastUpdated": "2026-11-05", "source": "https://models.viglet.org", "vendors": { "anthropic": [ { "id": "claude-fable-5", "label": "Claude Fable 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-07", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 59.9, "scores": { "coding": { "value": 76.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 64.08, "latencyTtftSec": 99.98, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-fable-5" }, { "id": "claude-fable-5-1", "label": "Claude Fable 5.1", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-08-28", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 49.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 66.59, "latencyTtftSec": 270.26, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-fable-5-1" }, { "id": "claude-haiku-4-5-20251001", "label": "Claude Haiku 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23.7, "scores": { "math": { "value": 39 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 82.98, "latencyTtftSec": 0.55, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-haiku-4-5-20251001" }, { "id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-10-07", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 36.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 232.05, "latencyTtftSec": 277.62, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-haiku-5-5" }, { "id": "claude-opus-4-20250514", "label": "Claude Opus 4", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 16.6, "scores": { "math": { "value": 36.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-20250514" }, { "id": "claude-opus-4-5-20251101", "label": "Claude Opus 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2025-11-24", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 34.7, "scores": { "math": { "value": 62.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 67.692, "latencyTtftSec": 1.324, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "anthropic-api", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-5-20251101" }, { "id": "claude-opus-4-6", "label": "Claude Opus 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-04", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 37.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 37.04, "latencyTtftSec": 1.72, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-6" }, { "id": "claude-opus-4-7", "label": "Claude Opus 4.7", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-14", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 53.5, "scores": { "coding": { "value": 73.6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 46.66, "latencyTtftSec": 27.73, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-7" }, { "id": "claude-opus-4-8", "label": "Claude Opus 4.8", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01", "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 55.7, "scores": { "coding": { "value": 74.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 58.82, "latencyTtftSec": 46.65, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-8" }, { "id": "claude-opus-5", "label": "Claude Opus 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-05", "releaseDate": "2026-07-24", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 44.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 49.98, "latencyTtftSec": 83.13, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-5" }, { "id": "claude-opus-5-5", "label": "Claude Opus 5.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-09-21", "pricing": { "inputPer1M": 4, "outputPer1M": 20, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 59.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 94.62, "latencyTtftSec": 646.35, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-opus-5-5" }, { "id": "claude-sonnet-4-20250514", "label": "Claude Sonnet 4", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 16.6, "scores": { "math": { "value": 38 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-4-20250514" }, { "id": "claude-sonnet-4-5-20250929", "label": "Claude Sonnet 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 19.3, "scores": { "math": { "value": 37 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 39.62, "latencyTtftSec": 1.04, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-4-5-20250929" }, { "id": "claude-sonnet-4-6", "label": "Claude Sonnet 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 35.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 43.07, "latencyTtftSec": 0.95, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-4-6" }, { "id": "claude-sonnet-5", "label": "Claude Sonnet 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-29", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 53.4, "scores": { "coding": { "value": 71.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 71.13, "latencyTtftSec": 237.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-5" }, { "id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-09-28", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 54.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 139.27, "latencyTtftSec": 389.26, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "anthropic-api", "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-5-5" } ], "azure": [ { "id": "gpt-4.1", "label": "GPT-4.1 (Azure)", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "azure", "ref": "azure/gpt-4.1" }, { "id": "gpt-4o", "label": "GPT-4o (Azure)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-09", "releaseDate": "2024-05-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "azure", "ref": "azure/gpt-4o" }, { "id": "gpt-4o-mini", "label": "GPT-4o mini (Azure)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-09", "releaseDate": "2024-07-18", "pricing": { "inputPer1M": 0.165, "outputPer1M": 0.66, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "azure", "ref": "azure/gpt-4o-mini" }, { "id": "gpt-5", "label": "GPT-5 (Azure)", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "azure", "ref": "azure/gpt-5" }, { "id": "o3", "label": "o3 (Azure)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "azure", "ref": "azure/o3" }, { "id": "o4-mini", "label": "o4-mini (Azure)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "azure", "ref": "azure/o4-mini" } ], "bedrock": [ { "id": "anthropic.claude-3-5-haiku-20241022-v1:0", "label": "Claude 3.5 Haiku", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bedrock", "ref": "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0" }, { "id": "anthropic.claude-3-5-sonnet-20241022-v2:0", "label": "Claude 3.5 Sonnet v2", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bedrock", "ref": "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0" }, { "id": "meta.llama3-1-70b-instruct-v1:0", "label": "Llama 3.1 70B Instruct", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 2048, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "pricing": { "inputPer1M": 0.99, "outputPer1M": 0.99, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "bedrock", "ref": "bedrock/meta.llama3-1-70b-instruct-v1:0" }, { "id": "mistral.mistral-large-2407-v1:0", "label": "Mistral Large", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8191, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bedrock", "ref": "bedrock/mistral.mistral-large-2407-v1:0" }, { "id": "amazon.titan-embed-text-v2:0", "label": "Titan Text Embeddings v2", "kind": "EMBEDDING", "contextWindow": 8192, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.02, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bedrock", "ref": "bedrock/amazon.titan-embed-text-v2:0" } ], "bfl": [ { "id": "flux-dev", "label": "flux-dev", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-dev" }, { "id": "flux-kontext-max", "label": "flux-kontext-max", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-kontext-max" }, { "id": "flux-kontext-pro", "label": "flux-kontext-pro", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-kontext-pro" }, { "id": "flux-pro", "label": "flux-pro", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-pro" }, { "id": "flux-pro-1.0-expand", "label": "flux-pro-1.0-expand", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-pro-1.0-expand" }, { "id": "flux-pro-1.0-fill", "label": "flux-pro-1.0-fill", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-pro-1.0-fill" }, { "id": "flux-pro-1.1", "label": "flux-pro-1.1", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-pro-1.1" }, { "id": "flux-pro-1.1-ultra", "label": "flux-pro-1.1-ultra", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "bfl", "ref": "bfl/flux-pro-1.1-ultra" } ], "cerebras": [ { "id": "gpt-oss-120b", "label": "GPT-OSS 120B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 0.35, "outputPer1M": 0.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 11.6, "scores": { "coding": { "value": 30.4 }, "math": { "value": 93.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 207.43, "latencyTtftSec": 0.79, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "cerebras", "ref": "cerebras/gpt-oss-120b" }, { "id": "llama-3.3-70b", "label": "Llama 3.3 70B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.85, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "cerebras", "ref": "cerebras/llama-3.3-70b" }, { "id": "llama3.1-8b", "label": "Llama 3.1 8B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "cerebras", "ref": "cerebras/llama3.1-8b" }, { "id": "qwen-3-32b", "label": "Qwen3 32B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "cerebras", "ref": "cerebras/qwen-3-32b" }, { "id": "zai-glm-4.6", "label": "GLM-4.6", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.25, "outputPer1M": 2.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "cerebras", "ref": "cerebras/zai-glm-4.6" } ], "cohere": [ { "id": "c4ai-aya-expanse-32b", "label": "Aya Expanse 32B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2024-10-24", "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/c4ai-aya-expanse-32b" }, { "id": "c4ai-aya-vision-32b", "label": "Aya Vision 32B", "kind": "CHAT", "contextWindow": 16000, "maxOutputTokens": 4000, "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-03-04", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/c4ai-aya-vision-32b" }, { "id": "command-a-03-2025", "label": "Command A", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-03-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-a-03-2025" }, { "id": "command-a-plus-05-2026", "label": "Command A Plus", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04-01", "releaseDate": "2026-05-20", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-a-plus-05-2026" }, { "id": "command-a-reasoning-08-2025", "label": "Command A Reasoning", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 32000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-08-21", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-a-reasoning-08-2025" }, { "id": "command-a-translate-08-2025", "label": "Command A Translate", "kind": "CHAT", "contextWindow": 8000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-08-28", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-a-translate-08-2025" }, { "id": "command-a-vision-07-2025", "label": "Command A Vision", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8000, "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-07-31", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-a-vision-07-2025" }, { "id": "command-r", "label": "Command R", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-r" }, { "id": "command-r-08-2024", "label": "Command R", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-r-08-2024" }, { "id": "command-r-plus", "label": "Command R+", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-r-plus" }, { "id": "command-r-plus-08-2024", "label": "Command R+", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-r-plus-08-2024" }, { "id": "command-r7b-12-2024", "label": "Command R7B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-12-13", "pricing": { "inputPer1M": 0.0375, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-r7b-12-2024" }, { "id": "command-r7b-arabic-02-2025", "label": "Command R7B Arabic", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-02-27", "pricing": { "inputPer1M": 0.0375, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/command-r7b-arabic-02-2025" }, { "id": "north-mini-code-1-0", "label": "North Mini Code", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-23", "releaseDate": "2026-06-09", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/north-mini-code-1-0" }, { "id": "north-small-translate-09-2026", "label": "North Small Translate", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 16000, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-09", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/north-small-translate-09-2026" }, { "id": "tiny-aya-earth", "label": "Tiny Aya Earth", "kind": "CHAT", "contextWindow": 8000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-17", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/tiny-aya-earth" }, { "id": "tiny-aya-fire", "label": "Tiny Aya Fire", "kind": "CHAT", "contextWindow": 8000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-17", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/tiny-aya-fire" }, { "id": "tiny-aya-global", "label": "Tiny Aya Global", "kind": "CHAT", "contextWindow": 8000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-17", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/tiny-aya-global" }, { "id": "tiny-aya-water", "label": "Tiny Aya Water", "kind": "CHAT", "contextWindow": 8000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-17", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/tiny-aya-water" }, { "id": "embed-multilingual-v3.0", "label": "Embed Multilingual v3", "kind": "EMBEDDING", "contextWindow": 1024, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/embed-multilingual-v3.0" }, { "id": "embed-v4.0", "label": "Embed v4", "kind": "EMBEDDING", "contextWindow": 128000, "embeddingDimensions": 1536, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/embed-v4.0" }, { "id": "rerank-v3.5", "label": "Rerank v3.5", "kind": "RERANK", "contextWindow": 4096, "maxOutputTokens": 4096, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "cohere", "ref": "cohere/rerank-v3.5" } ], "deepseek": [ { "id": "deepseek-chat", "label": "DeepSeek-V3", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "parameters": 671000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.28, "outputPer1M": 0.42, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "deepseek", "ref": "deepseek/deepseek-chat" }, { "id": "deepseek-flash", "label": "DeepSeek V4.1 Flash 1017", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 393216, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-10-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "deepseek", "ref": "deepseek/deepseek-flash" }, { "id": "deepseek-reasoner", "label": "DeepSeek-R1", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "reasoning" ], "openWeights": true, "parameters": 671000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.28, "outputPer1M": 0.42, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "deepseek", "ref": "deepseek/deepseek-reasoner" }, { "id": "deepseek-v4-flash", "label": "DeepSeek V4 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 393216, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-10-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 128.05, "latencyTtftSec": 1.55, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "deepseek", "ref": "deepseek/deepseek-v4-flash" }, { "id": "deepseek-v4-flash-vision-exp", "label": "DeepSeek V4 Flash Vision Exp", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 393216, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-10-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "deepseek", "ref": "deepseek/deepseek-v4-flash-vision-exp" }, { "id": "deepseek-v4-pro", "label": "DeepSeek V4 Pro", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 393216, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-13", "pricing": { "inputPer1M": 1.32, "outputPer1M": 3.96, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 23.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 72.02, "latencyTtftSec": 1.59, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "deepseek", "ref": "deepseek/deepseek-v4-pro" } ], "elevenlabs": [ { "id": "eleven_english_sts_v2", "label": "Eleven English v2 (speech-to-speech)", "kind": "SPEECH", "modalities": { "input": [ "audio" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_english_sts_v2" }, { "id": "eleven_flash_v2", "label": "Eleven Flash v2", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_flash_v2" }, { "id": "eleven_flash_v2_5", "label": "Eleven Flash v2.5", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_flash_v2_5" }, { "id": "eleven_multilingual_sts_v2", "label": "Eleven Multilingual v2 (speech-to-speech)", "kind": "SPEECH", "modalities": { "input": [ "audio" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_multilingual_sts_v2" }, { "id": "eleven_multilingual_v2", "label": "Eleven Multilingual v2", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_multilingual_v2" }, { "id": "eleven_turbo_v2", "label": "Eleven Turbo v2", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_turbo_v2" }, { "id": "eleven_turbo_v2_5", "label": "Eleven Turbo v2.5", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_turbo_v2_5" }, { "id": "eleven_v3", "label": "Eleven v3", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_v3" }, { "id": "eleven_v3_conversational", "label": "Eleven v3 Conversational", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_v3_conversational" }, { "id": "eleven_v4", "label": "Eleven v4", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_v4" }, { "id": "eleven_v4_turbo", "label": "Eleven v4 Turbo", "kind": "SPEECH", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "elevenlabs-api" ], "lastVerified": "2026-11-05", "vendor": "elevenlabs", "ref": "elevenlabs/eleven_v4_turbo" } ], "fireworks": [ { "id": "accounts/fireworks/models/deepseek-r1", "label": "DeepSeek-R1", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 20480, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "fireworks", "ref": "fireworks/accounts/fireworks/models/deepseek-r1" }, { "id": "accounts/fireworks/models/deepseek-v3", "label": "DeepSeek-V3", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.9, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "fireworks", "ref": "fireworks/accounts/fireworks/models/deepseek-v3" }, { "id": "accounts/fireworks/models/glm-4p5-air", "label": "GLM-4.5 Air", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 96000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.22, "outputPer1M": 0.88, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "fireworks", "ref": "fireworks/accounts/fireworks/models/glm-4p5-air" }, { "id": "accounts/fireworks/models/glm-4p6", "label": "GLM-4.6", "kind": "CHAT", "contextWindow": 202800, "maxOutputTokens": 202800, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.19, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "fireworks", "ref": "fireworks/accounts/fireworks/models/glm-4p6" } ], "gemini": [ { "id": "antigravity-preview-05-2026", "label": "Antigravity Agent Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "sources": [ "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/antigravity-preview-05-2026" }, { "id": "antigravity-preview-09-2026", "label": "Antigravity Agent Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "sources": [ "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/antigravity-preview-09-2026" }, { "id": "antigravity-preview-latest", "label": "Antigravity Agent Preview Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "sources": [ "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/antigravity-preview-latest" }, { "id": "deep-research-max-preview-04-2026", "label": "Deep Research Max Preview (Apr-21-2026)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-21", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/deep-research-max-preview-04-2026" }, { "id": "deep-research-preview-04-2026", "label": "Deep Research Preview (Apr-21-2026)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-21", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/deep-research-preview-04-2026" }, { "id": "deep-research-pro-preview-12-2025", "label": "Deep Research Pro Preview (Dec-12-2025) [Rerouted]", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/deep-research-pro-preview-12-2025" }, { "id": "gemini-2.5-computer-use-preview-10-2025", "label": "Gemini 2.5 Computer Use Preview 10-2025", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-10-07", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-computer-use-preview-10-2025" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 9.9, "scores": { "math": { "value": 60.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 191.51, "latencyTtftSec": 0.37, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash" }, { "id": "gemini-2.5-flash-image", "label": "Nano Banana", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-26", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-image" }, { "id": "gemini-2.5-flash-lite", "label": "Gemini 2.5 Flash-Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.9, "scores": { "math": { "value": 35.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 299.13, "latencyTtftSec": 0.29, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-lite" }, { "id": "gemini-2.5-flash-preview-tts", "label": "Gemini 2.5 Flash Preview TTS", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-05-01", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-preview-tts" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 16.1, "scores": { "coding": { "value": 33.3 }, "math": { "value": 87.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 108, "latencyTtftSec": 25.24, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-pro" }, { "id": "gemini-2.5-pro-preview-tts", "label": "Gemini 2.5 Pro Preview TTS", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "audio" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-05-01", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-pro-preview-tts" }, { "id": "gemini-3-flash-preview", "label": "Gemini 3 Flash Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-12-17", "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3-flash-preview" }, { "id": "gemini-3-pro-image", "label": "Nano Banana Pro", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3-pro-image" }, { "id": "gemini-3-pro-image-preview", "label": "Nano Banana Pro", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3-pro-image-preview" }, { "id": "gemini-3.1-flash-image", "label": "Nano Banana 2", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-image" }, { "id": "gemini-3.1-flash-image-preview", "label": "Nano Banana 2", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-image-preview" }, { "id": "gemini-3.1-flash-lite", "label": "Gemini 3.1 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-07", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-lite" }, { "id": "gemini-3.1-flash-lite-image", "label": "Nano Banana 2 Lite", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "vision", "reasoning", "tools" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-30", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-lite-image" }, { "id": "gemini-3.1-flash-lite-preview", "label": "Gemini 3.1 Flash Lite Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-03", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 325.24, "latencyTtftSec": 4.64, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-lite-preview" }, { "id": "gemini-3.1-flash-tts-preview", "label": "Gemini 3.1 Flash TTS Preview", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "capabilities": [ "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-15", "pricing": { "inputPer1M": 1, "outputPer1M": 20, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-tts-preview" }, { "id": "gemini-3.1-pro-preview", "label": "Gemini 3.1 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 46.5, "scores": { "coding": { "value": 68.8 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 127.77, "latencyTtftSec": 23.98, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-pro-preview" }, { "id": "gemini-3.1-pro-preview-customtools", "label": "Gemini 3.1 Pro Preview Custom Tools", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-pro-preview-customtools" }, { "id": "gemini-3.5-flash", "label": "Gemini 3.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-19", "pricing": { "inputPer1M": 1.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 50.2, "scores": { "coding": { "value": 70.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 172.01, "latencyTtftSec": 14.91, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.5-flash" }, { "id": "gemini-3.5-flash-lite", "label": "Gemini 3.5 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-07-21", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 11.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 379.05, "latencyTtftSec": 6.97, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.5-flash-lite" }, { "id": "gemini-3.5-transcribe", "label": "Gemini 3.5 Transcribe", "kind": "CHAT", "contextWindow": 98304, "maxOutputTokens": 32768, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.5-transcribe" }, { "id": "gemini-3.6-flash", "label": "Gemini 3.6 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-07-21", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 50.1, "scores": { "coding": { "value": 69.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 176.54, "latencyTtftSec": 16.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.6-flash" }, { "id": "gemini-3.7-flash", "label": "Gemini 3.7 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-08-13", "pricing": { "inputPer1M": 0.75, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.7-flash" }, { "id": "gemini-3.8-flash", "label": "Gemini 3.8 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 0.75, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 30.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 121.59, "latencyTtftSec": 27.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.8-flash" }, { "id": "gemini-3.8-flash-lite-tts", "label": "Gemini 3.8 Flash Lite TTS", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.8-flash-lite-tts" }, { "id": "gemini-3.8-flash-tts", "label": "Gemini 3.8 Flash TTS", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.8-flash-tts" }, { "id": "gemini-4-argon", "label": "Gemini 4 Argon", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-10-13", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 50.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 86.66, "latencyTtftSec": 58.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-4-argon" }, { "id": "gemini-flash-latest", "label": "Gemini Flash Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-flash-latest" }, { "id": "gemini-flash-lite-latest", "label": "Gemini Flash-Lite Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-flash-lite-latest" }, { "id": "gemini-nano-banana-2.1", "label": "Nano Banana 2.1", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-nano-banana-2.1" }, { "id": "gemini-omni-1.1-flash", "label": "Gemini Omni 1.1 Flash", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text", "video" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-omni-1.1-flash" }, { "id": "gemini-omni-flash-preview", "label": "Gemini Omni Flash Preview", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text", "video" ] }, "releaseDate": "2026-06-30", "pricing": { "inputPer1M": 1.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-omni-flash-preview" }, { "id": "gemini-pro-latest", "label": "Gemini Pro Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-pro-latest" }, { "id": "gemini-robotics-er-2-preview", "label": "Gemini Robotics-ER 2 Preview", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-robotics-er-2-preview" }, { "id": "gemma-4-26b-a4b-it", "label": "Gemma 4 26B A4B IT", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-02", "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemma-4-26b-a4b-it" }, { "id": "gemma-4-31b-it", "label": "Gemma 4 31B IT", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-02", "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemma-4-31b-it" }, { "id": "lyria-3-clip-preview", "label": "Lyria 3 Clip Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "releaseDate": "2026-03-25", "sources": [ "gemini-api", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/lyria-3-clip-preview" }, { "id": "lyria-3-pro-preview", "label": "Lyria 3 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "releaseDate": "2026-03-25", "sources": [ "gemini-api", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/lyria-3-pro-preview" }, { "id": "lyria-3.5", "label": "Lyria 3.5", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/lyria-3.5" }, { "id": "nano-banana-pro-preview", "label": "Nano Banana Pro", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/nano-banana-pro-preview" }, { "id": "gemini-embedding-001", "label": "Gemini Embedding 001", "kind": "EMBEDDING", "contextWindow": 2048, "maxOutputTokens": 1, "embeddingDimensions": 3072, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2025-05-20", "pricing": { "inputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-embedding-001" }, { "id": "gemini-embedding-2", "label": "Gemini Embedding 2", "kind": "EMBEDDING", "contextWindow": 8192, "maxOutputTokens": 1, "embeddingDimensions": 3072, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "embedding" ] }, "knowledgeCutoff": "2025-11", "releaseDate": "2026-04-22", "pricing": { "inputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-embedding-2" }, { "id": "gemini-embedding-2-preview", "label": "Gemini Embedding 2 Preview", "kind": "EMBEDDING", "contextWindow": 8192, "maxOutputTokens": 1, "embeddingDimensions": 3072, "capabilities": [ "vision" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-embedding-2-preview" }, { "id": "veo-3.1-fast-generate-001", "label": "veo-3.1-fast-generate-001", "kind": "VIDEO", "contextWindow": 1024, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/veo-3.1-fast-generate-001" }, { "id": "veo-3.1-fast-generate-preview", "label": "Veo 3.1 fast", "kind": "VIDEO", "contextWindow": 480, "maxOutputTokens": 8192, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/veo-3.1-fast-generate-preview" }, { "id": "veo-3.1-generate-001", "label": "veo-3.1-generate-001", "kind": "VIDEO", "contextWindow": 1024, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/veo-3.1-generate-001" }, { "id": "veo-3.1-generate-preview", "label": "Veo 3.1", "kind": "VIDEO", "contextWindow": 480, "maxOutputTokens": 8192, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/veo-3.1-generate-preview" }, { "id": "veo-3.1-lite-generate-preview", "label": "Veo 3.1 lite", "kind": "VIDEO", "contextWindow": 480, "maxOutputTokens": 8192, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/veo-3.1-lite-generate-preview" }, { "id": "aqa", "label": "Model that performs Attributed Question Answering.", "kind": "UNKNOWN", "contextWindow": 7168, "maxOutputTokens": 1024, "sources": [ "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/aqa" }, { "id": "gemini-2.5-flash-native-audio-latest", "label": "Gemini 2.5 Flash Native Audio Latest", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 8192, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-native-audio-latest" }, { "id": "gemini-2.5-flash-native-audio-preview-09-2025", "label": "Gemini 2.5 Flash Native Audio Preview 09-2025", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 8192, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-native-audio-preview-09-2025" }, { "id": "gemini-2.5-flash-native-audio-preview-12-2025", "label": "Gemini 2.5 Flash Native Audio Preview 12-2025", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-native-audio-preview-12-2025" }, { "id": "gemini-3.1-flash-live-preview", "label": "Gemini 3.1 Flash Live Preview", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-26", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-live-preview" }, { "id": "gemini-3.5-live-translate-preview", "label": "Gemini 3.5 Live Translate Preview", "kind": "UNKNOWN", "contextWindow": 16384, "maxOutputTokens": 32768, "openWeights": false, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-09", "pricing": { "inputPer1M": 3.5, "outputPer1M": 21, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.5-live-translate-preview" }, { "id": "gemini-3.5-transcribe-live", "label": "Gemini 3.5 Transcribe Live", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 65536, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 3.5, "outputPer1M": 21, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.5-transcribe-live" }, { "id": "gemini-3.8-live", "label": "Gemini 3.8 Live", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.8-live" }, { "id": "gemini-3.8-live-extended-thinking", "label": "Gemini 3.8 Live Extended Thinking", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-3.8-live-extended-thinking" }, { "id": "gemini-robotics-er-2-streaming-preview", "label": "Gemini Robotics-ER 2 Streaming Preview", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "gemini-api", "litellm" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/gemini-robotics-er-2-streaming-preview" }, { "id": "lyria-realtime-exp", "label": "Lyria Realtime Experimental", "kind": "UNKNOWN", "contextWindow": 1048576, "maxOutputTokens": 65536, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "gemini-api" ], "lastVerified": "2026-11-05", "vendor": "gemini", "ref": "gemini/lyria-realtime-exp" } ], "gemini-openai": [ { "id": "gemini-1.5-flash", "label": "Gemini 1.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-1.5-flash" }, { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-1.5-pro" }, { "id": "gemini-2.0-flash", "label": "Gemini 2.0 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-2.0-flash" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-2.5-flash" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-2.5-pro" } ], "groq": [ { "id": "llama-3.1-8b-instant", "label": "Llama 3.1 8B Instant", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "parameters": 8000000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.08, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/llama-3.1-8b-instant" }, { "id": "llama-3.3-70b-versatile", "label": "Llama 3.3 70B Versatile", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "parameters": 70000000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "pricing": { "inputPer1M": 0.59, "outputPer1M": 0.79, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/llama-3.3-70b-versatile" }, { "id": "meta-llama/llama-4-maverick-17b-128e-instruct", "label": "Llama 4 Maverick 17B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": true, "parameters": 400000000000, "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/meta-llama/llama-4-maverick-17b-128e-instruct" }, { "id": "meta-llama/llama-4-scout-17b-16e-instruct", "label": "Llama 4 Scout 17B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": true, "parameters": 109000000000, "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.11, "outputPer1M": 0.34, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/meta-llama/llama-4-scout-17b-16e-instruct" }, { "id": "moonshotai/kimi-k2-instruct-0905", "label": "Kimi K2 Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": true, "parameters": 1000000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/moonshotai/kimi-k2-instruct-0905" }, { "id": "openai/gpt-oss-120b", "label": "GPT-OSS 120B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32766, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 117000000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/openai/gpt-oss-120b" }, { "id": "openai/gpt-oss-20b", "label": "GPT-OSS 20B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 21000000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.9, "scores": { "coding": { "value": 20.7 }, "math": { "value": 89.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 245.179, "latencyTtftSec": 0.422, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/openai/gpt-oss-20b" }, { "id": "qwen/qwen3-32b", "label": "Qwen3 32B", "kind": "CHAT", "contextWindow": 131000, "maxOutputTokens": 131000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 32000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.29, "outputPer1M": 0.59, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "groq", "ref": "groq/qwen/qwen3-32b" } ], "meta": [ { "id": "muse-spark-1.1", "label": "Muse Spark 1.1", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-08", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 201.22, "latencyTtftSec": 12.75, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "meta", "ref": "meta/muse-spark-1.1" }, { "id": "muse-spark-1.2", "label": "Muse Spark 1.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-05", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 227.82, "latencyTtftSec": 12.41, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "meta", "ref": "meta/muse-spark-1.2" }, { "id": "muse-spark-1.2-contributor", "label": "Muse Spark 1.2 Contributor", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-05", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "meta", "ref": "meta/muse-spark-1.2-contributor" }, { "id": "muse-spark-1.3", "label": "Muse Spark 1.3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 36.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 123.9, "latencyTtftSec": 42.09, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "meta", "ref": "meta/muse-spark-1.3" }, { "id": "muse-spark-1.3-contributor", "label": "Muse Spark 1.3 Contributor", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "meta", "ref": "meta/muse-spark-1.3-contributor" }, { "id": "muse-wonder-1.0", "label": "Muse Wonder", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-12", "pricing": { "inputPer1M": 4, "outputPer1M": 20, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "meta", "ref": "meta/muse-wonder-1.0" } ], "minimax": [ { "id": "MiniMax-M2", "label": "MiniMax M2", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-10-27", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 28.3, "scores": { "math": { "value": 78.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 101.85, "latencyTtftSec": 1.43, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M2" }, { "id": "MiniMax-M2.1", "label": "MiniMax-M2.1", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-23", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 44.36, "latencyTtftSec": 1.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M2.1" }, { "id": "MiniMax-M2.5", "label": "MiniMax-M2.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-12", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 43.45, "latencyTtftSec": 1.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M2.5" }, { "id": "MiniMax-M2.5-highspeed", "label": "MiniMax-M2.5-highspeed", "kind": "CHAT", "contextWindow": 204800, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-13", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M2.5-highspeed" }, { "id": "MiniMax-M2.7", "label": "MiniMax-M2.7", "kind": "CHAT", "contextWindow": 204800, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-18", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 47.82, "latencyTtftSec": 1.69, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M2.7" }, { "id": "MiniMax-M2.7-highspeed", "label": "MiniMax-M2.7-highspeed", "kind": "CHAT", "contextWindow": 204800, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-18", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M2.7-highspeed" }, { "id": "MiniMax-M3", "label": "MiniMax M3", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-06-01", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 18.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 106.4, "latencyTtftSec": 0.82, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M3" }, { "id": "MiniMax-M3.1-Flash", "label": "MiniMax-M3.1-Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 524288, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-19", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 29.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 138.01, "latencyTtftSec": 1.11, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-M3.1-Flash" }, { "id": "MiniMax-H3", "label": "MiniMax-H3", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-H3" }, { "id": "MiniMax-H3-Max", "label": "MiniMax-H3-Max", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "minimax", "ref": "minimax/MiniMax-H3-Max" } ], "mistral": [ { "id": "codestral-2508", "label": "Codestral 25.08", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-30", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/codestral-2508" }, { "id": "codestral-latest", "label": "Codestral", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8191, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10", "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/codestral-latest" }, { "id": "deepseek-v4-1-flash-1017", "label": "DeepSeek V4.1 Flash 1017", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-10-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/deepseek-v4-1-flash-1017" }, { "id": "devstral-2512", "label": "Devstral 2", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/devstral-2512" }, { "id": "devstral-latest", "label": "Devstral 2", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/devstral-latest" }, { "id": "devstral-medium-latest", "label": "Devstral 2 (latest)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/devstral-medium-latest" }, { "id": "glm-5-2", "label": "GLM-5.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-13", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/glm-5-2" }, { "id": "labs-devstral-small-2512", "label": "Devstral Small 2", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/labs-devstral-small-2512" }, { "id": "labs-leanstral-1-5-1", "label": "Leanstral 1.5", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-30", "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/labs-leanstral-1-5-1" }, { "id": "magistral-medium-latest", "label": "Magistral Medium (latest)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/magistral-medium-latest" }, { "id": "ministral-14b-2512", "label": "Ministral 3 14B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/ministral-14b-2512" }, { "id": "ministral-3b-2512", "label": "Ministral 3 3B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/ministral-3b-2512" }, { "id": "ministral-3b-latest", "label": "Ministral 3B (latest)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/ministral-3b-latest" }, { "id": "ministral-8b-2512", "label": "Ministral 3 8B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/ministral-8b-2512" }, { "id": "ministral-8b-latest", "label": "Ministral 8B (latest)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/ministral-8b-latest" }, { "id": "mistral-large-2512", "label": "Mistral Large 3", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-11", "releaseDate": "2024-11-01", "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-large-2512" }, { "id": "mistral-large-4", "label": "Mistral Large 4", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 1048576, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-06", "pricing": { "inputPer1M": 1.36, "outputPer1M": 4.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 26.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-large-4" }, { "id": "mistral-large-4-0-8", "label": "Mistral Large 4.0.8", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-06", "pricing": { "inputPer1M": 0.7, "outputPer1M": 2.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-large-4-0-8" }, { "id": "mistral-large-latest", "label": "Mistral Large", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-11", "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-large-latest" }, { "id": "mistral-medium-2505", "label": "Mistral Medium 3", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2025-05-07", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-medium-2505" }, { "id": "mistral-medium-2508", "label": "Mistral Medium 3.1", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2025-08-12", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-medium-2508" }, { "id": "mistral-medium-2604", "label": "Mistral Medium 3.5", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-29", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-medium-2604" }, { "id": "mistral-medium-latest", "label": "Mistral Medium (latest)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-medium-latest" }, { "id": "mistral-small-2506", "label": "Mistral Small 3.2", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03", "releaseDate": "2025-06-20", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-small-2506" }, { "id": "mistral-small-2603", "label": "Mistral Small 4", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06", "releaseDate": "2026-03-16", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-small-2603" }, { "id": "mistral-small-latest", "label": "Mistral Small", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06", "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-small-latest" }, { "id": "open-mistral-nemo", "label": "Mistral Nemo", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07", "releaseDate": "2024-07-01", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/open-mistral-nemo" }, { "id": "pixtral-12b", "label": "Pixtral 12B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09", "releaseDate": "2024-09-01", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/pixtral-12b" }, { "id": "voxtral-small-2507", "label": "Voxtral Small", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "audio", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-15", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/voxtral-small-2507" }, { "id": "voxtral-small-latest", "label": "Voxtral Small (latest)", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "audio", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/voxtral-small-latest" }, { "id": "zai-glm-5-2", "label": "GLM-5.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-13", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/zai-glm-5-2" }, { "id": "zai-glm-5-3", "label": "GLM-5.3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-14", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/zai-glm-5-3" }, { "id": "zai-glm-5-3-flash", "label": "GLM-5.3-Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-26", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/zai-glm-5-3-flash" }, { "id": "mistral-embed", "label": "Mistral Embed", "kind": "EMBEDDING", "contextWindow": 8192, "embeddingDimensions": 1024, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "releaseDate": "2023-12-11", "pricing": { "inputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/mistral-embed" }, { "id": "voxtral-mini-latest", "label": "Voxtral Mini (latest)", "kind": "TRANSCRIPTION", "openWeights": false, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/voxtral-mini-latest" }, { "id": "voxtral-mini-tts-latest", "label": "Voxtral Mini TTS (latest)", "kind": "SPEECH", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "mistral", "ref": "mistral/voxtral-mini-tts-latest" } ], "moonshot": [ { "id": "kimi-k2.6", "label": "Kimi K2.6", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-20", "pricing": { "inputPer1M": 0.95, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 43.37, "latencyTtftSec": 2.89, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "moonshot", "ref": "moonshot/kimi-k2.6" }, { "id": "kimi-k2.7-code", "label": "Kimi K2.7 Code", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "pricing": { "inputPer1M": 0.95, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 43.93, "latencyTtftSec": 2.75, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "moonshot", "ref": "moonshot/kimi-k2.7-code" }, { "id": "kimi-k2.7-code-highspeed", "label": "Kimi K2.7 Code HighSpeed", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "pricing": { "inputPer1M": 1.9, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "moonshot", "ref": "moonshot/kimi-k2.7-code-highspeed" }, { "id": "kimi-k3", "label": "Kimi K3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 1048576, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-07-16", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 46.41, "latencyTtftSec": 3.81, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "moonshot", "ref": "moonshot/kimi-k3" }, { "id": "kimi-k3.1-pro", "label": "Kimi K3.1 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 1048576, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-23", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 46.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 27.53, "latencyTtftSec": 3.23, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "moonshot", "ref": "moonshot/kimi-k3.1-pro" }, { "id": "kimi-k3.1-pro-highspeed", "label": "Kimi K3.1 Pro Highspeed", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 1048576, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-23", "pricing": { "inputPer1M": 4, "outputPer1M": 20, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "moonshot", "ref": "moonshot/kimi-k3.1-pro-highspeed" } ], "ollama": [ { "id": "alfred", "label": "alfred", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/alfred" }, { "id": "athene-v2", "label": "athene-v2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/athene-v2" }, { "id": "autotrust-jev", "label": "autotrust-jev", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/autotrust-jev" }, { "id": "aya", "label": "aya", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/aya" }, { "id": "aya-expanse", "label": "aya-expanse", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/aya-expanse" }, { "id": "bakllava", "label": "bakllava", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/bakllava" }, { "id": "beam", "label": "beam", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/beam" }, { "id": "bespoke-minicheck", "label": "bespoke-minicheck", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/bespoke-minicheck" }, { "id": "bonsai-2", "label": "bonsai-2", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/bonsai-2" }, { "id": "clef", "label": "clef", "kind": "CHAT", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/clef" }, { "id": "clef-flash", "label": "clef-flash", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/clef-flash" }, { "id": "codebooga", "label": "codebooga", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codebooga" }, { "id": "codegeex4", "label": "codegeex4", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 8192, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codegeex4" }, { "id": "codegemma", "label": "codegemma", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codegemma" }, { "id": "codellama", "label": "codellama", "kind": "CHAT", "contextWindow": 4096, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codellama" }, { "id": "codeqwen", "label": "codeqwen", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codeqwen" }, { "id": "codestral", "label": "codestral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codestral" }, { "id": "codeup", "label": "codeup", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/codeup" }, { "id": "cogito", "label": "cogito", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/cogito" }, { "id": "cogito-2.1", "label": "cogito-2.1", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/cogito-2.1" }, { "id": "command-a", "label": "command-a", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/command-a" }, { "id": "command-r", "label": "command-r", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/command-r" }, { "id": "command-r-plus", "label": "command-r-plus", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/command-r-plus" }, { "id": "command-r7b", "label": "command-r7b", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/command-r7b" }, { "id": "command-r7b-arabic", "label": "command-r7b-arabic", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/command-r7b-arabic" }, { "id": "d1", "label": "d1", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/d1" }, { "id": "d1-omni", "label": "d1-omni", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/d1-omni" }, { "id": "d3", "label": "d3", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/d3" }, { "id": "dbrx", "label": "dbrx", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 5.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dbrx" }, { "id": "deepcoder", "label": "deepcoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepcoder" }, { "id": "deepscaler", "label": "deepscaler", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepscaler" }, { "id": "deepseek-coder", "label": "deepseek-coder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-coder" }, { "id": "deepseek-coder-v2", "label": "deepseek-coder-v2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-coder-v2" }, { "id": "deepseek-llm", "label": "deepseek-llm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-llm" }, { "id": "deepseek-ocr", "label": "deepseek-ocr", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-ocr" }, { "id": "deepseek-r1", "label": "deepseek-r1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-r1" }, { "id": "deepseek-v2", "label": "deepseek-v2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 5.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v2" }, { "id": "deepseek-v2.5", "label": "deepseek-v2.5", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 6.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v2.5" }, { "id": "deepseek-v3", "label": "deepseek-v3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v3" }, { "id": "deepseek-v3.1", "label": "deepseek-v3.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 13.7, "scores": { "math": { "value": 49.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 96.14, "latencyTtftSec": 1.32, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v3.1" }, { "id": "deepseek-v4-flash", "label": "deepseek-v4-flash", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v4-flash" }, { "id": "deepseek-v4-pro", "label": "deepseek-v4-pro", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v4-pro" }, { "id": "deepseek-v4.1-flash", "label": "deepseek-v4.1-flash", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/deepseek-v4.1-flash" }, { "id": "devstral", "label": "devstral", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/devstral" }, { "id": "devstral-2", "label": "devstral-2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 8.6, "scores": { "coding": { "value": 31.3 }, "math": { "value": 36.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 58.329, "latencyTtftSec": 0.781, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/devstral-2" }, { "id": "devstral-small-2", "label": "devstral-small-2", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 7.5, "scores": { "coding": { "value": 29.3 }, "math": { "value": 34.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 30.239, "latencyTtftSec": 0.654, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/devstral-small-2" }, { "id": "dolphin-llama3", "label": "dolphin-llama3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dolphin-llama3" }, { "id": "dolphin-mistral", "label": "dolphin-mistral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dolphin-mistral" }, { "id": "dolphin-mixtral", "label": "dolphin-mixtral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dolphin-mixtral" }, { "id": "dolphin-phi", "label": "dolphin-phi", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dolphin-phi" }, { "id": "dolphin3", "label": "dolphin3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dolphin3" }, { "id": "dolphincoder", "label": "dolphincoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/dolphincoder" }, { "id": "duckdb-nsql", "label": "duckdb-nsql", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/duckdb-nsql" }, { "id": "everythinglm", "label": "everythinglm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/everythinglm" }, { "id": "exaone-deep", "label": "exaone-deep", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/exaone-deep" }, { "id": "exaone3.5", "label": "exaone3.5", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/exaone3.5" }, { "id": "falcon", "label": "falcon", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/falcon" }, { "id": "falcon2", "label": "falcon2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/falcon2" }, { "id": "falcon3", "label": "falcon3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/falcon3" }, { "id": "firefunction-v2", "label": "firefunction-v2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/firefunction-v2" }, { "id": "flint", "label": "flint", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/flint" }, { "id": "functiongemma", "label": "functiongemma", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/functiongemma" }, { "id": "gemini-3-flash-preview", "label": "gemini-3-flash-preview", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gemini-3-flash-preview" }, { "id": "gemma", "label": "gemma", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gemma" }, { "id": "gemma2", "label": "Gemma 2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gemma2" }, { "id": "gemma3", "label": "gemma3", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gemma3" }, { "id": "gemma3n", "label": "gemma3n", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gemma3n" }, { "id": "gemma4", "label": "gemma4", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gemma4" }, { "id": "glm-4.7-flash", "label": "glm-4.7-flash", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm-4.7-flash" }, { "id": "glm-5.1", "label": "glm-5.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm-5.1" }, { "id": "glm-5.2", "label": "glm-5.2", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm-5.2" }, { "id": "glm-5.3", "label": "glm-5.3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm-5.3" }, { "id": "glm-5.3-flash", "label": "glm-5.3-flash", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm-5.3-flash" }, { "id": "glm-ocr", "label": "glm-ocr", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm-ocr" }, { "id": "glm4", "label": "glm4", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/glm4" }, { "id": "goliath", "label": "goliath", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/goliath" }, { "id": "gpt-oss", "label": "gpt-oss", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gpt-oss" }, { "id": "gpt-oss-safeguard", "label": "gpt-oss-safeguard", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/gpt-oss-safeguard" }, { "id": "granite-code", "label": "granite-code", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite-code" }, { "id": "granite3-dense", "label": "granite3-dense", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3-dense" }, { "id": "granite3-guardian", "label": "granite3-guardian", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3-guardian" }, { "id": "granite3-moe", "label": "granite3-moe", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3-moe" }, { "id": "granite3.1-dense", "label": "granite3.1-dense", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3.1-dense" }, { "id": "granite3.1-moe", "label": "granite3.1-moe", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3.1-moe" }, { "id": "granite3.2", "label": "granite3.2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3.2" }, { "id": "granite3.2-vision", "label": "granite3.2-vision", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3.2-vision" }, { "id": "granite3.3", "label": "granite3.3", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite3.3" }, { "id": "granite4", "label": "granite4", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite4" }, { "id": "granite4.1", "label": "granite4.1", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite4.1" }, { "id": "granite4.1-guardian", "label": "granite4.1-guardian", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite4.1-guardian" }, { "id": "granite4.2", "label": "granite4.2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite4.2" }, { "id": "hermes3", "label": "hermes3", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/hermes3" }, { "id": "internlm2", "label": "internlm2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/internlm2" }, { "id": "kev", "label": "kev", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/kev" }, { "id": "kimi-k2.5", "label": "kimi-k2.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/kimi-k2.5" }, { "id": "kimi-k2.6", "label": "kimi-k2.6", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/kimi-k2.6" }, { "id": "kimi-k2.7-code", "label": "kimi-k2.7-code", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/kimi-k2.7-code" }, { "id": "kimi-k3", "label": "kimi-k3", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/kimi-k3" }, { "id": "kimi-k3.1-pro", "label": "kimi-k3.1-pro", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/kimi-k3.1-pro" }, { "id": "laguna-s-2.1", "label": "laguna-s-2.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/laguna-s-2.1" }, { "id": "laguna-xs-2.1", "label": "laguna-xs-2.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/laguna-xs-2.1" }, { "id": "laguna-xs.2", "label": "laguna-xs.2", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/laguna-xs.2" }, { "id": "lfm2", "label": "lfm2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm2" }, { "id": "lfm2.5", "label": "lfm2.5", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm2.5" }, { "id": "lfm2.5-thinking", "label": "lfm2.5-thinking", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm2.5-thinking" }, { "id": "lfm3", "label": "lfm3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm3" }, { "id": "lfm3-audio", "label": "lfm3-audio", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm3-audio" }, { "id": "lfm3-omni", "label": "lfm3-omni", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm3-omni" }, { "id": "lfm3-vl", "label": "lfm3-vl", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/lfm3-vl" }, { "id": "llama-guard3", "label": "llama-guard3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama-guard3" }, { "id": "llama-pro", "label": "llama-pro", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama-pro" }, { "id": "llama2", "label": "llama2", "kind": "CHAT", "contextWindow": 4096, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama2" }, { "id": "llama2-chinese", "label": "llama2-chinese", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama2-chinese" }, { "id": "llama2-uncensored", "label": "llama2-uncensored", "kind": "CHAT", "contextWindow": 4096, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama2-uncensored" }, { "id": "llama3", "label": "llama3", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3" }, { "id": "llama3-chatqa", "label": "llama3-chatqa", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3-chatqa" }, { "id": "llama3-gradient", "label": "llama3-gradient", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3-gradient" }, { "id": "llama3-groq-tool-use", "label": "llama3-groq-tool-use", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3-groq-tool-use" }, { "id": "llama3.1", "label": "Llama 3.1", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3.1" }, { "id": "llama3.2", "label": "Llama 3.2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3.2" }, { "id": "llama3.2-vision", "label": "llama3.2-vision", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3.2-vision" }, { "id": "llama3.3", "label": "llama3.3", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama3.3" }, { "id": "llama4", "label": "llama4", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llama4" }, { "id": "llava", "label": "llava", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llava" }, { "id": "llava-llama3", "label": "llava-llama3", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llava-llama3" }, { "id": "llava-phi3", "label": "llava-phi3", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/llava-phi3" }, { "id": "magicoder", "label": "magicoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/magicoder" }, { "id": "magistral", "label": "magistral", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/magistral" }, { "id": "marco-o1", "label": "marco-o1", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/marco-o1" }, { "id": "mathstral", "label": "mathstral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mathstral" }, { "id": "medgemma", "label": "medgemma", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/medgemma" }, { "id": "medgemma1.5", "label": "medgemma1.5", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/medgemma1.5" }, { "id": "meditron", "label": "meditron", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/meditron" }, { "id": "medllama2", "label": "medllama2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/medllama2" }, { "id": "megadolphin", "label": "megadolphin", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/megadolphin" }, { "id": "mimo-v2.6", "label": "mimo-v2.6", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mimo-v2.6" }, { "id": "mimo-v2.6-flash", "label": "mimo-v2.6-flash", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mimo-v2.6-flash" }, { "id": "mimo-v2.6-pro", "label": "mimo-v2.6-pro", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mimo-v2.6-pro" }, { "id": "minicpm-v", "label": "minicpm-v", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minicpm-v" }, { "id": "minicpm-v4.5", "label": "minicpm-v4.5", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minicpm-v4.5" }, { "id": "minicpm-v4.6", "label": "minicpm-v4.6", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minicpm-v4.6" }, { "id": "minimax-m2.5", "label": "minimax-m2.5", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minimax-m2.5" }, { "id": "minimax-m2.7", "label": "minimax-m2.7", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minimax-m2.7" }, { "id": "minimax-m3", "label": "minimax-m3", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minimax-m3" }, { "id": "minimax-m3.1-flash", "label": "minimax-m3.1-flash", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/minimax-m3.1-flash" }, { "id": "ministral-3", "label": "ministral-3", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/ministral-3" }, { "id": "mistral", "label": "Mistral", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral" }, { "id": "mistral-large", "label": "mistral-large", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-large" }, { "id": "mistral-large-3", "label": "mistral-large-3", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 9.3, "scores": { "coding": { "value": 20.1 }, "math": { "value": 38 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 89.08, "latencyTtftSec": 1.07, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-large-3" }, { "id": "mistral-large-4", "label": "mistral-large-4", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 26, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 169.058, "latencyTtftSec": 2.881, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-large-4" }, { "id": "mistral-medium-3.5", "label": "mistral-medium-3.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-medium-3.5" }, { "id": "mistral-nemo", "label": "mistral-nemo", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-nemo" }, { "id": "mistral-openorca", "label": "mistral-openorca", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-openorca" }, { "id": "mistral-small", "label": "mistral-small", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 5.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-small" }, { "id": "mistral-small3.1", "label": "mistral-small3.1", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 7.1, "scores": { "coding": { "value": 26.3 }, "math": { "value": 3.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 60.25, "latencyTtftSec": 0.98, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-small3.1" }, { "id": "mistral-small3.2", "label": "mistral-small3.2", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 8.2, "scores": { "coding": { "value": 12.5 }, "math": { "value": 27 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 47.24, "latencyTtftSec": 0.89, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistral-small3.2" }, { "id": "mistrallite", "label": "mistrallite", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mistrallite" }, { "id": "mixtral", "label": "mixtral", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mixtral" }, { "id": "moondream", "label": "moondream", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/moondream" }, { "id": "muse-glimmer", "label": "muse-glimmer", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 6.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 111, "latencyTtftSec": 1.09, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/muse-glimmer" }, { "id": "muse-spark-open", "label": "muse-spark-open", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/muse-spark-open" }, { "id": "nemotron", "label": "nemotron", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron" }, { "id": "nemotron-3-nano", "label": "nemotron-3-nano", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-3-nano" }, { "id": "nemotron-3-super", "label": "nemotron-3-super", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-3-super" }, { "id": "nemotron-3-ultra", "label": "nemotron-3-ultra", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-3-ultra" }, { "id": "nemotron-3.5-bolt", "label": "nemotron-3.5-bolt", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-3.5-bolt" }, { "id": "nemotron-3.5-lightning", "label": "nemotron-3.5-lightning", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-3.5-lightning" }, { "id": "nemotron-3.5-super", "label": "nemotron-3.5-super", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-3.5-super" }, { "id": "nemotron-cascade-2", "label": "nemotron-cascade-2", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-cascade-2" }, { "id": "nemotron-mini", "label": "nemotron-mini", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron-mini" }, { "id": "nemotron3", "label": "nemotron3", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nemotron3" }, { "id": "neural-chat", "label": "neural-chat", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/neural-chat" }, { "id": "nexusraven", "label": "nexusraven", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nexusraven" }, { "id": "nimble", "label": "nimble", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nimble" }, { "id": "nimble-v3", "label": "nimble-v3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nimble-v3" }, { "id": "north-mini-code-1.0", "label": "north-mini-code-1.0", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/north-mini-code-1.0" }, { "id": "notus", "label": "notus", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/notus" }, { "id": "notux", "label": "notux", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/notux" }, { "id": "nous-hermes", "label": "nous-hermes", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nous-hermes" }, { "id": "nous-hermes2", "label": "nous-hermes2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nous-hermes2" }, { "id": "nous-hermes2-mixtral", "label": "nous-hermes2-mixtral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nous-hermes2-mixtral" }, { "id": "nuextract", "label": "nuextract", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nuextract" }, { "id": "olmo-3", "label": "olmo-3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/olmo-3" }, { "id": "olmo-3.1", "label": "olmo-3.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/olmo-3.1" }, { "id": "olmo2", "label": "olmo2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/olmo2" }, { "id": "open-orca-platypus2", "label": "open-orca-platypus2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/open-orca-platypus2" }, { "id": "openchat", "label": "openchat", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/openchat" }, { "id": "opencoder", "label": "opencoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/opencoder" }, { "id": "openhermes", "label": "openhermes", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/openhermes" }, { "id": "openthinker", "label": "openthinker", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/openthinker" }, { "id": "orca-mini", "label": "orca-mini", "kind": "CHAT", "contextWindow": 4096, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/orca-mini" }, { "id": "orca2", "label": "orca2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/orca2" }, { "id": "ornith", "label": "ornith", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/ornith" }, { "id": "ornith-1.5", "label": "ornith-1.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/ornith-1.5" }, { "id": "phi", "label": "phi", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi" }, { "id": "phi3", "label": "Phi-3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi3" }, { "id": "phi3.5", "label": "phi3.5", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi3.5" }, { "id": "phi4", "label": "phi4", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi4" }, { "id": "phi4-mini", "label": "phi4-mini", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 6.3, "scores": { "coding": { "value": 3.8 }, "math": { "value": 6.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 44.94, "latencyTtftSec": 0.86, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi4-mini" }, { "id": "phi4-mini-reasoning", "label": "phi4-mini-reasoning", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi4-mini-reasoning" }, { "id": "phi4-reasoning", "label": "phi4-reasoning", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phi4-reasoning" }, { "id": "phind-codellama", "label": "phind-codellama", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phind-codellama" }, { "id": "phonon", "label": "phonon", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/phonon" }, { "id": "pplx-decider", "label": "pplx-decider", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/pplx-decider" }, { "id": "pplx-decider-flash", "label": "pplx-decider-flash", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/pplx-decider-flash" }, { "id": "qwen", "label": "qwen", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen" }, { "id": "qwen2", "label": "qwen2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen2" }, { "id": "qwen2-math", "label": "qwen2-math", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen2-math" }, { "id": "qwen2.5", "label": "Qwen 2.5", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen2.5" }, { "id": "qwen2.5-coder", "label": "qwen2.5-coder", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen2.5-coder" }, { "id": "qwen2.5vl", "label": "qwen2.5vl", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen2.5vl" }, { "id": "qwen3", "label": "qwen3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3" }, { "id": "qwen3-coder", "label": "qwen3-coder", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3-coder" }, { "id": "qwen3-coder-next", "label": "qwen3-coder-next", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3-coder-next" }, { "id": "qwen3-next", "label": "qwen3-next", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3-next" }, { "id": "qwen3-vl", "label": "qwen3-vl", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3-vl" }, { "id": "qwen3.5", "label": "qwen3.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3.5" }, { "id": "qwen3.6", "label": "qwen3.6", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3.6" }, { "id": "qwen3.8", "label": "qwen3.8", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3.8" }, { "id": "qwen3.8-flash-next", "label": "qwen3.8-flash-next", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "performance": { "throughputTps": 51.06, "latencyTtftSec": 2.33, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3.8-flash-next" }, { "id": "qwq", "label": "qwq", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwq" }, { "id": "r1-1776", "label": "r1-1776", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 6.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/r1-1776" }, { "id": "reader-lm", "label": "reader-lm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/reader-lm" }, { "id": "reflection", "label": "reflection", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/reflection" }, { "id": "rnj-1", "label": "rnj-1", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/rnj-1" }, { "id": "sailor2", "label": "sailor2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/sailor2" }, { "id": "samantha-mistral", "label": "samantha-mistral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/samantha-mistral" }, { "id": "shieldgemma", "label": "shieldgemma", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/shieldgemma" }, { "id": "smallthinker", "label": "smallthinker", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/smallthinker" }, { "id": "smollm", "label": "smollm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/smollm" }, { "id": "smollm2", "label": "smollm2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/smollm2" }, { "id": "solar", "label": "solar", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/solar" }, { "id": "solar-pro", "label": "solar-pro", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/solar-pro" }, { "id": "sqlcoder", "label": "sqlcoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/sqlcoder" }, { "id": "stable-beluga", "label": "stable-beluga", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/stable-beluga" }, { "id": "stable-code", "label": "stable-code", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/stable-code" }, { "id": "stablelm-zephyr", "label": "stablelm-zephyr", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/stablelm-zephyr" }, { "id": "stablelm2", "label": "stablelm2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/stablelm2" }, { "id": "starcoder", "label": "starcoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/starcoder" }, { "id": "starcoder2", "label": "starcoder2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/starcoder2" }, { "id": "starling-lm", "label": "starling-lm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/starling-lm" }, { "id": "strands-decider", "label": "strands-decider", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/strands-decider" }, { "id": "tev1", "label": "tev1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/tev1" }, { "id": "tinydolphin", "label": "tinydolphin", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/tinydolphin" }, { "id": "tinyllama", "label": "tinyllama", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/tinyllama" }, { "id": "translategemma", "label": "translategemma", "kind": "CHAT", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/translategemma" }, { "id": "tulu3", "label": "tulu3", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/tulu3" }, { "id": "vicuna", "label": "vicuna", "kind": "CHAT", "contextWindow": 2048, "maxOutputTokens": 2048, "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "litellm", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/vicuna" }, { "id": "wizard-math", "label": "wizard-math", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizard-math" }, { "id": "wizard-vicuna", "label": "wizard-vicuna", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizard-vicuna" }, { "id": "wizard-vicuna-uncensored", "label": "wizard-vicuna-uncensored", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizard-vicuna-uncensored" }, { "id": "wizardcoder", "label": "wizardcoder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizardcoder" }, { "id": "wizardlm", "label": "wizardlm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizardlm" }, { "id": "wizardlm-uncensored", "label": "wizardlm-uncensored", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizardlm-uncensored" }, { "id": "wizardlm2", "label": "wizardlm2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/wizardlm2" }, { "id": "xwinlm", "label": "xwinlm", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/xwinlm" }, { "id": "yarn-llama2", "label": "yarn-llama2", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/yarn-llama2" }, { "id": "yarn-mistral", "label": "yarn-mistral", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/yarn-mistral" }, { "id": "yi", "label": "yi", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/yi" }, { "id": "yi-coder", "label": "yi-coder", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/yi-coder" }, { "id": "zephyr", "label": "zephyr", "kind": "CHAT", "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/zephyr" }, { "id": "all-minilm", "label": "all-minilm", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/all-minilm" }, { "id": "bge-large", "label": "bge-large", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/bge-large" }, { "id": "bge-m3", "label": "bge-m3", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/bge-m3" }, { "id": "embeddinggemma", "label": "embeddinggemma", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/embeddinggemma" }, { "id": "embeddinggemma-2", "label": "embeddinggemma-2", "kind": "EMBEDDING", "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/embeddinggemma-2" }, { "id": "granite-embedding", "label": "granite-embedding", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/granite-embedding" }, { "id": "laya", "label": "laya", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/laya" }, { "id": "mxbai-embed-large", "label": "mxbai-embed-large", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/mxbai-embed-large" }, { "id": "nomic-embed-text", "label": "nomic-embed-text", "kind": "EMBEDDING", "embeddingDimensions": 768, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nomic-embed-text" }, { "id": "nomic-embed-text-v2-moe", "label": "nomic-embed-text-v2-moe", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/nomic-embed-text-v2-moe" }, { "id": "paraphrase-multilingual", "label": "paraphrase-multilingual", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/paraphrase-multilingual" }, { "id": "qwen3-embedding", "label": "qwen3-embedding", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/qwen3-embedding" }, { "id": "snowflake-arctic-embed", "label": "snowflake-arctic-embed", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/snowflake-arctic-embed" }, { "id": "snowflake-arctic-embed2", "label": "snowflake-arctic-embed2", "kind": "EMBEDDING", "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "sources": [ "ollama-library" ], "lastVerified": "2026-11-05", "vendor": "ollama", "ref": "ollama/snowflake-arctic-embed2" } ], "openai": [ { "id": "chat-latest", "label": "chat-latest", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/chat-latest" }, { "id": "gpt-4.1", "label": "GPT-4.1", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "vision", "tools" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "performance": { "throughputTps": 151.52, "latencyTtftSec": 1.09, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4.1" }, { "id": "gpt-4.1-2025-04-14", "label": "gpt-4.1-2025-04-14", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4.1-2025-04-14" }, { "id": "gpt-4.1-mini", "label": "GPT-4.1 mini", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "vision", "tools" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.8, "scores": { "coding": { "value": 20.2 }, "math": { "value": 46.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 140.4, "latencyTtftSec": 0.81, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4.1-mini" }, { "id": "gpt-4.1-mini-2025-04-14", "label": "gpt-4.1-mini-2025-04-14", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4.1-mini-2025-04-14" }, { "id": "gpt-4o", "label": "GPT-4o", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "vision", "tools" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-09", "releaseDate": "2024-05-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 8.4, "scores": { "math": { "value": 6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 162.41, "latencyTtftSec": 0.91, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o" }, { "id": "gpt-4o-2024-08-06", "label": "gpt-4o-2024-08-06", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-09", "releaseDate": "2024-08-06", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 121.69, "latencyTtftSec": 1.17, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-2024-08-06" }, { "id": "gpt-4o-2024-11-20", "label": "gpt-4o-2024-11-20", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-09", "releaseDate": "2024-11-20", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-2024-11-20" }, { "id": "gpt-4o-mini", "label": "GPT-4o mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "vision", "tools" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-09", "releaseDate": "2024-07-18", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 6.7, "scores": { "coding": { "value": 11.4 }, "math": { "value": 14.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 96.27, "latencyTtftSec": 1.09, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini" }, { "id": "gpt-4o-mini-2024-07-18", "label": "gpt-4o-mini-2024-07-18", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-2024-07-18" }, { "id": "gpt-5", "label": "gpt-5", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23, "scores": { "coding": { "value": 37.8 }, "math": { "value": 94.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 89.53, "latencyTtftSec": 79.87, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5" }, { "id": "gpt-5-2025-08-07", "label": "gpt-5-2025-08-07", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-2025-08-07" }, { "id": "gpt-5-mini", "label": "gpt-5-mini", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 16.8, "scores": { "coding": { "value": 15.6 }, "math": { "value": 90.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 93.68, "latencyTtftSec": 59.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-mini" }, { "id": "gpt-5-mini-2025-08-07", "label": "gpt-5-mini-2025-08-07", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-mini-2025-08-07" }, { "id": "gpt-5-nano", "label": "gpt-5-nano", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 13, "scores": { "math": { "value": 83.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 145.66, "latencyTtftSec": 75.09, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-nano" }, { "id": "gpt-5-nano-2025-08-07", "label": "gpt-5-nano-2025-08-07", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-nano-2025-08-07" }, { "id": "gpt-5-pro", "label": "gpt-5-pro", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-10-06", "pricing": { "inputPer1M": 15, "outputPer1M": 120, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-pro" }, { "id": "gpt-5-pro-2025-10-06", "label": "gpt-5-pro-2025-10-06", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 120, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-pro-2025-10-06" }, { "id": "gpt-5-search-api", "label": "gpt-5-search-api", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-search-api" }, { "id": "gpt-5-search-api-2025-10-14", "label": "gpt-5-search-api-2025-10-14", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5-search-api-2025-10-14" }, { "id": "gpt-5.1", "label": "gpt-5.1", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 36.9, "scores": { "coding": { "value": 49.4 }, "math": { "value": 94 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 101.59, "latencyTtftSec": 45.51, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.1" }, { "id": "gpt-5.1-2025-11-13", "label": "gpt-5.1-2025-11-13", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.1-2025-11-13" }, { "id": "gpt-5.2", "label": "gpt-5.2", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 42.2, "scores": { "math": { "value": 99 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 67.18, "latencyTtftSec": 162.63, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.2" }, { "id": "gpt-5.2-2025-12-11", "label": "gpt-5.2-2025-12-11", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.2-2025-12-11" }, { "id": "gpt-5.2-pro", "label": "gpt-5.2-pro", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "pricing": { "inputPer1M": 21, "outputPer1M": 168, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.2-pro" }, { "id": "gpt-5.2-pro-2025-12-11", "label": "gpt-5.2-pro-2025-12-11", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 21, "outputPer1M": 168, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.2-pro-2025-12-11" }, { "id": "gpt-5.3-codex", "label": "gpt-5.3-codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 44.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 81.56, "latencyTtftSec": 84.34, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.3-codex" }, { "id": "gpt-5.4", "label": "gpt-5.4", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 51.4, "scores": { "coding": { "value": 71.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 80.97, "latencyTtftSec": 211.68, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4" }, { "id": "gpt-5.4-2026-03-05", "label": "gpt-5.4-2026-03-05", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-2026-03-05" }, { "id": "gpt-5.4-mini", "label": "gpt-5.4-mini", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 40, "scores": { "coding": { "value": 56.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 234.72, "latencyTtftSec": 119.42, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-mini" }, { "id": "gpt-5.4-mini-2026-03-17", "label": "gpt-5.4-mini-2026-03-17", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-mini-2026-03-17" }, { "id": "gpt-5.4-nano", "label": "gpt-5.4-nano", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 38.2, "scores": { "coding": { "value": 56.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 156.63, "latencyTtftSec": 109.81, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-nano" }, { "id": "gpt-5.4-nano-2026-03-17", "label": "gpt-5.4-nano-2026-03-17", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-nano-2026-03-17" }, { "id": "gpt-5.4-pro", "label": "gpt-5.4-pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-pro" }, { "id": "gpt-5.4-pro-2026-03-05", "label": "gpt-5.4-pro-2026-03-05", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.4-pro-2026-03-05" }, { "id": "gpt-5.5", "label": "gpt-5.5", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 54.8, "scores": { "coding": { "value": 74.9 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 72.7, "latencyTtftSec": 54.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.5" }, { "id": "gpt-5.5-2026-04-23", "label": "gpt-5.5-2026-04-23", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.5-2026-04-23" }, { "id": "gpt-5.5-pro", "label": "gpt-5.5-pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.5-pro" }, { "id": "gpt-5.5-pro-2026-04-23", "label": "gpt-5.5-pro-2026-04-23", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.5-pro-2026-04-23" }, { "id": "gpt-5.6-luna", "label": "gpt-5.6-luna", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 113.31, "latencyTtftSec": 110.62, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.6-luna" }, { "id": "gpt-5.6-sol", "label": "gpt-5.6-sol", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 58.9, "scores": { "coding": { "value": 77.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 116.37, "latencyTtftSec": 85.88, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.6-sol" }, { "id": "gpt-5.6-terra", "label": "gpt-5.6-terra", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 32.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 112.2, "latencyTtftSec": 195.75, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-5.6-terra" }, { "id": "gpt-6-astra", "label": "gpt-6-astra", "kind": "CHAT", "contextWindow": 922000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-04-30", "releaseDate": "2026-09-04", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 56.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 47.02, "latencyTtftSec": 354.26, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-6-astra" }, { "id": "gpt-6-luna", "label": "gpt-6-luna", "kind": "CHAT", "contextWindow": 922000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-05-18", "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 27.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 113.82, "latencyTtftSec": 125.11, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-6-luna" }, { "id": "gpt-6-sol", "label": "gpt-6-sol", "kind": "CHAT", "contextWindow": 922000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-04-20", "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 44.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 130.28, "latencyTtftSec": 91.17, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-6-sol" }, { "id": "gpt-6.1-sol", "label": "gpt-6.1-sol", "kind": "CHAT", "contextWindow": 922000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-04-30", "releaseDate": "2026-09-29", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 54.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 60.43, "latencyTtftSec": 324.29, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-6.1-sol" }, { "id": "gpt-6.1-terra", "label": "gpt-6.1-terra", "kind": "CHAT", "contextWindow": 922000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06-01", "releaseDate": "2026-10-26", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 51.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 107.05, "latencyTtftSec": 362.72, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-6.1-terra" }, { "id": "gpt-audio", "label": "gpt-audio", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-audio" }, { "id": "gpt-live-1", "label": "gpt-live-1", "kind": "CHAT", "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-live-1" }, { "id": "o3", "label": "o3", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 20.2, "scores": { "math": { "value": 88.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 122.75, "latencyTtftSec": 7.87, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/o3" }, { "id": "o3-2025-04-16", "label": "o3-2025-04-16", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/o3-2025-04-16" }, { "id": "o3-pro", "label": "o3-pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05", "releaseDate": "2025-06-10", "pricing": { "inputPer1M": 20, "outputPer1M": 80, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 21.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/o3-pro" }, { "id": "o3-pro-2025-06-10", "label": "o3-pro-2025-06-10", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 20, "outputPer1M": 80, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/o3-pro-2025-06-10" }, { "id": "text-embedding-3-large", "label": "text-embedding-3-large", "kind": "EMBEDDING", "contextWindow": 8191, "embeddingDimensions": 3072, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "knowledgeCutoff": "2024-01", "releaseDate": "2024-01-25", "pricing": { "inputPer1M": 0.13, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "openai-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/text-embedding-3-large" }, { "id": "text-embedding-3-small", "label": "text-embedding-3-small", "kind": "EMBEDDING", "contextWindow": 8191, "embeddingDimensions": 1536, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "knowledgeCutoff": "2024-01", "releaseDate": "2024-01-25", "pricing": { "inputPer1M": 0.02, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "openai-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/text-embedding-3-small" }, { "id": "text-embedding-ada-002", "label": "text-embedding-ada-002", "kind": "EMBEDDING", "contextWindow": 8191, "embeddingDimensions": 1536, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "knowledgeCutoff": "2022-12", "releaseDate": "2022-12-15", "pricing": { "inputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/text-embedding-ada-002" }, { "id": "chatgpt-image-latest", "label": "chatgpt-image-latest", "kind": "IMAGE", "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/chatgpt-image-latest" }, { "id": "gpt-image-1-mini", "label": "gpt-image-1-mini", "kind": "IMAGE", "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "releaseDate": "2025-09-26", "pricing": { "inputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-1-mini" }, { "id": "gpt-image-1.5", "label": "gpt-image-1.5", "kind": "IMAGE", "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "releaseDate": "2025-11-25", "pricing": { "inputPer1M": 5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-1.5" }, { "id": "gpt-image-2", "label": "gpt-image-2", "kind": "IMAGE", "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image" ] }, "releaseDate": "2026-04-21", "pricing": { "inputPer1M": 5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2" }, { "id": "gpt-image-2-2026-04-21", "label": "gpt-image-2-2026-04-21", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2-2026-04-21" }, { "id": "gpt-image-2.5-flare", "label": "gpt-image-2.5-flare", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2.5-flare" }, { "id": "gpt-image-2.5-flare-2026-09-08", "label": "gpt-image-2.5-flare-2026-09-08", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2.5-flare-2026-09-08" }, { "id": "gpt-image-2.5-sunburst", "label": "gpt-image-2.5-sunburst", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2.5-sunburst" }, { "id": "gpt-image-2.5-sunburst-2026-09-08", "label": "gpt-image-2.5-sunburst-2026-09-08", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2.5-sunburst-2026-09-08" }, { "id": "gpt-image-2.6-flare", "label": "gpt-image-2.6-flare", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-11-05" }, "sources": [ "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2.6-flare" }, { "id": "gpt-image-2.6-sunburst", "label": "gpt-image-2.6-sunburst", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-11-05" }, "sources": [ "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-image-2.6-sunburst" }, { "id": "gpt-4o-mini-transcribe", "label": "gpt-4o-mini-transcribe", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-transcribe" }, { "id": "gpt-4o-mini-transcribe-2025-03-20", "label": "gpt-4o-mini-transcribe-2025-03-20", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-transcribe-2025-03-20" }, { "id": "gpt-4o-mini-transcribe-2025-12-15", "label": "gpt-4o-mini-transcribe-2025-12-15", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-transcribe-2025-12-15" }, { "id": "gpt-4o-transcribe", "label": "gpt-4o-transcribe", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "status": "DEPRECATED", "deprecated": true, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "openai-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-transcribe" }, { "id": "gpt-4o-transcribe-diarize", "label": "gpt-4o-transcribe-diarize", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-transcribe-diarize" }, { "id": "gpt-live-transcribe", "label": "gpt-live-transcribe", "kind": "TRANSCRIPTION", "openWeights": false, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "status": "GA", "sources": [ "openai-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-live-transcribe" }, { "id": "gpt-realtime-whisper", "label": "gpt-realtime-whisper", "kind": "TRANSCRIPTION", "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "status": "DEPRECATED", "deprecated": true, "sources": [ "openai-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-whisper" }, { "id": "gpt-transcribe", "label": "gpt-transcribe", "kind": "TRANSCRIPTION", "openWeights": false, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "status": "GA", "sources": [ "openai-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-transcribe" }, { "id": "whisper-1", "label": "whisper-1", "kind": "TRANSCRIPTION", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/whisper-1" }, { "id": "gpt-4o-mini-tts", "label": "gpt-4o-mini-tts", "kind": "SPEECH", "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-tts" }, { "id": "gpt-4o-mini-tts-2025-03-20", "label": "gpt-4o-mini-tts-2025-03-20", "kind": "SPEECH", "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-tts-2025-03-20" }, { "id": "gpt-4o-mini-tts-2025-12-15", "label": "gpt-4o-mini-tts-2025-12-15", "kind": "SPEECH", "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-4o-mini-tts-2025-12-15" }, { "id": "gpt-audio-1.5", "label": "gpt-audio-1.5", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-audio-1.5" }, { "id": "gpt-audio-2025-08-28", "label": "gpt-audio-2025-08-28", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-audio-2025-08-28" }, { "id": "gpt-audio-mini", "label": "gpt-audio-mini", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-audio-mini" }, { "id": "gpt-audio-mini-2025-12-15", "label": "gpt-audio-mini-2025-12-15", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-audio-mini-2025-12-15" }, { "id": "gpt-realtime", "label": "gpt-realtime", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime" }, { "id": "gpt-realtime-1.5", "label": "gpt-realtime-1.5", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-1.5" }, { "id": "gpt-realtime-2", "label": "gpt-realtime-2", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-2" }, { "id": "gpt-realtime-2.1", "label": "gpt-realtime-2.1", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2026-07-06", "pricing": { "inputPer1M": 4, "outputPer1M": 24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-2.1" }, { "id": "gpt-realtime-2.1-mini", "label": "gpt-realtime-2.1-mini", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-2.1-mini" }, { "id": "gpt-realtime-2025-08-28", "label": "gpt-realtime-2025-08-28", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-2025-08-28" }, { "id": "gpt-realtime-mini", "label": "gpt-realtime-mini", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-mini" }, { "id": "gpt-realtime-mini-2025-12-15", "label": "gpt-realtime-mini-2025-12-15", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-mini-2025-12-15" }, { "id": "gpt-realtime-translate", "label": "gpt-realtime-translate", "kind": "SPEECH", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/gpt-realtime-translate" }, { "id": "tts-1", "label": "tts-1", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/tts-1" }, { "id": "tts-1-1106", "label": "tts-1-1106", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/tts-1-1106" }, { "id": "tts-1-hd", "label": "tts-1-hd", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/tts-1-hd" }, { "id": "tts-1-hd-1106", "label": "tts-1-hd-1106", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/tts-1-hd-1106" }, { "id": "sora-2", "label": "sora-2", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/sora-2" }, { "id": "sora-2-pro", "label": "sora-2-pro", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/sora-2-pro" }, { "id": "omni-moderation-2024-09-26", "label": "omni-moderation-2024-09-26", "kind": "MODERATION", "contextWindow": 32768, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/omni-moderation-2024-09-26" }, { "id": "omni-moderation-latest", "label": "omni-moderation-latest", "kind": "MODERATION", "contextWindow": 32768, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-11-05", "vendor": "openai", "ref": "openai/omni-moderation-latest" } ], "openrouter": [ { "id": "~anthropic/claude-fable-latest", "label": "Anthropic: Claude Fable Latest", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-fable-latest" }, { "id": "~anthropic/claude-haiku-latest", "label": "Anthropic Claude Haiku Latest", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-haiku-latest" }, { "id": "~anthropic/claude-opus-latest", "label": "Anthropic: Claude Opus Latest", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-opus-latest" }, { "id": "~anthropic/claude-sonnet-latest", "label": "Anthropic Claude Sonnet Latest", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-31", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-sonnet-latest" }, { "id": "~deepseek/deepseek-flash-latest", "label": "DeepSeek: DeepSeek Flash Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~deepseek/deepseek-flash-latest" }, { "id": "~deepseek/deepseek-pro-latest", "label": "DeepSeek: DeepSeek Pro Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 384000, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.32, "outputPer1M": 3.96, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~deepseek/deepseek-pro-latest" }, { "id": "~deepseek/deepseek-v4-flash-latest", "label": "DeepSeek: DeepSeek V4 Flash Latest", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.04, "outputPer1M": 0.64, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~deepseek/deepseek-v4-flash-latest" }, { "id": "~google/gemini-flash-latest", "label": "Google Gemini Flash Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-01", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~google/gemini-flash-latest" }, { "id": "~google/gemini-pro-latest", "label": "Google Gemini Pro Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~google/gemini-pro-latest" }, { "id": "~moonshotai/kimi-latest", "label": "MoonshotAI Kimi Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~moonshotai/kimi-latest" }, { "id": "~openai/gpt-astra-latest", "label": "OpenAI: GPT Astra Latest", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-astra-latest" }, { "id": "~openai/gpt-luna-latest", "label": "OpenAI: GPT Luna Latest", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-luna-latest" }, { "id": "~openai/gpt-mini-latest", "label": "OpenAI GPT Mini Latest", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-mini-latest" }, { "id": "~openai/gpt-sol-latest", "label": "OpenAI: GPT Sol Latest", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-sol-latest" }, { "id": "~openai/gpt-terra-latest", "label": "OpenAI: GPT Terra Latest", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-terra-latest" }, { "id": "~unbiased/pareto-latest", "label": "Pareto Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~unbiased/pareto-latest" }, { "id": "~x-ai/grok-latest", "label": "xAI: Grok Latest", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 450000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~x-ai/grok-latest" }, { "id": "~z-ai/glm-flash-latest", "label": "Z.ai: GLM Flash Latest", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~z-ai/glm-flash-latest" }, { "id": "~z-ai/glm-latest", "label": "Z.ai: GLM Latest", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.6538, "outputPer1M": 2.0548, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/~z-ai/glm-latest" }, { "id": "aion-labs/aion-2.0", "label": "AionLabs: Aion-2.0", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-21", "pricing": { "inputPer1M": 0.8, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-2.0" }, { "id": "aion-labs/aion-3.0", "label": "AionLabs: Aion-3.0", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-05", "pricing": { "inputPer1M": 3, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-3.0" }, { "id": "aion-labs/aion-3.0-mini", "label": "AionLabs: Aion-3.0-Mini", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-14", "pricing": { "inputPer1M": 0.7, "outputPer1M": 1.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-3.0-mini" }, { "id": "aion-labs/aion-3.5", "label": "AionLabs: Aion 3.5", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-23", "pricing": { "inputPer1M": 3, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-3.5" }, { "id": "aion-labs/aion-3.5-mini", "label": "AionLabs: Aion 3.5 Mini", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-23", "pricing": { "inputPer1M": 0.7, "outputPer1M": 1.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-3.5-mini" }, { "id": "aion-labs/aion-rp-llama-3.1-8b", "label": "AionLabs: Aion-RP 1.0 (8B)", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2025-02-04", "pricing": { "inputPer1M": 0.8, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-rp-llama-3.1-8b" }, { "id": "amazon/nova-2-lite-v1", "label": "Amazon: Nova 2 Lite", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-10", "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/amazon/nova-2-lite-v1" }, { "id": "amazon/nova-lite-v1", "label": "Amazon: Nova Lite 1.0", "kind": "CHAT", "contextWindow": 300000, "maxOutputTokens": 5120, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-12-05", "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/amazon/nova-lite-v1" }, { "id": "amazon/nova-micro-v1", "label": "Amazon: Nova Micro 1.0", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 5120, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-12-05", "pricing": { "inputPer1M": 0.035, "outputPer1M": 0.14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/amazon/nova-micro-v1" }, { "id": "amazon/nova-premier-v1", "label": "Amazon: Nova Premier 1.0", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10", "releaseDate": "2025-04-30", "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/amazon/nova-premier-v1" }, { "id": "amazon/nova-pro-v1", "label": "Amazon: Nova Pro 1.0", "kind": "CHAT", "contextWindow": 300000, "maxOutputTokens": 5120, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-12-05", "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/amazon/nova-pro-v1" }, { "id": "anthracite-org/magnum-v4-72b", "label": "Magnum v4 72B", "kind": "CHAT", "contextWindow": 16384, "maxOutputTokens": 2048, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-10-22", "pricing": { "inputPer1M": 3, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthracite-org/magnum-v4-72b" }, { "id": "anthropic/claude-3-haiku", "label": "Claude 3 Haiku (via OpenRouter)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-08-31", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 5.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-3-haiku" }, { "id": "anthropic/claude-fable-5", "label": "Anthropic: Claude Fable 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-09", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-fable-5" }, { "id": "anthropic/claude-fable-5:batch", "label": "Anthropic: Claude Fable 5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-fable-5:batch" }, { "id": "anthropic/claude-fable-5.1", "label": "Anthropic: Claude Fable 5.1", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-09-01", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-fable-5.1" }, { "id": "anthropic/claude-fable-5.1:batch", "label": "Anthropic: Claude Fable 5.1 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-fable-5.1:batch" }, { "id": "anthropic/claude-haiku-4.5", "label": "Anthropic: Claude Haiku 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 200000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-haiku-4.5" }, { "id": "anthropic/claude-haiku-4.5:batch", "label": "Anthropic: Claude Haiku 4.5 (batch)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-haiku-4.5:batch" }, { "id": "anthropic/claude-haiku-5.5", "label": "Anthropic: Claude Haiku 5.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-10-07", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-haiku-5.5" }, { "id": "anthropic/claude-haiku-5.5:batch", "label": "Anthropic: Claude Haiku 5.5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-haiku-5.5:batch" }, { "id": "anthropic/claude-opus-4.1", "label": "Anthropic: Claude Opus 4.1", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 15, "outputPer1M": 75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.1" }, { "id": "anthropic/claude-opus-4.1:batch", "label": "Anthropic: Claude Opus 4.1 (batch)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 7.5, "outputPer1M": 37.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.1:batch" }, { "id": "anthropic/claude-opus-4.5", "label": "Anthropic: Claude Opus 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2025-11-24", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 23.7, "scores": { "math": { "value": 62.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 46.86, "latencyTtftSec": 1.17, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.5" }, { "id": "anthropic/claude-opus-4.5:batch", "label": "Anthropic: Claude Opus 4.5 (batch)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.5:batch" }, { "id": "anthropic/claude-opus-4.6", "label": "Anthropic: Claude Opus 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.6" }, { "id": "anthropic/claude-opus-4.6:batch", "label": "Anthropic: Claude Opus 4.6 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.6:batch" }, { "id": "anthropic/claude-opus-4.7", "label": "Anthropic: Claude Opus 4.7", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.7" }, { "id": "anthropic/claude-opus-4.7:batch", "label": "Anthropic: Claude Opus 4.7 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.7:batch" }, { "id": "anthropic/claude-opus-4.8", "label": "Anthropic: Claude Opus 4.8", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01", "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.8" }, { "id": "anthropic/claude-opus-4.8:batch", "label": "Anthropic: Claude Opus 4.8 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.8:batch" }, { "id": "anthropic/claude-opus-5", "label": "Claude Opus 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-05", "releaseDate": "2026-07-24", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-5" }, { "id": "anthropic/claude-opus-5:batch", "label": "Anthropic: Claude Opus 5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-5:batch" }, { "id": "anthropic/claude-opus-5.5", "label": "Anthropic: Claude Opus 5.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 4, "outputPer1M": 20, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-5.5" }, { "id": "anthropic/claude-opus-5.5:batch", "label": "Anthropic: Claude Opus 5.5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-5.5:batch" }, { "id": "anthropic/claude-sonnet-4.5", "label": "Claude Sonnet 4.5 (via OpenRouter)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 1000000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-09-29", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "openrouter-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4.5" }, { "id": "anthropic/claude-sonnet-4.5:batch", "label": "Anthropic: Claude Sonnet 4.5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4.5:batch" }, { "id": "anthropic/claude-sonnet-4.6", "label": "Anthropic: Claude Sonnet 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4.6" }, { "id": "anthropic/claude-sonnet-4.6:batch", "label": "Anthropic: Claude Sonnet 4.6 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4.6:batch" }, { "id": "anthropic/claude-sonnet-5", "label": "Anthropic: Claude Sonnet 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-30", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-5" }, { "id": "anthropic/claude-sonnet-5:batch", "label": "Anthropic: Claude Sonnet 5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-5:batch" }, { "id": "anthropic/claude-sonnet-5.5", "label": "Anthropic: Claude Sonnet 5.5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06", "releaseDate": "2026-09-28", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-5.5" }, { "id": "anthropic/claude-sonnet-5.5:batch", "label": "Anthropic: Claude Sonnet 5.5 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-5.5:batch" }, { "id": "bytedance-seed/seed-1.6", "label": "ByteDance Seed: Seed 1.6", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2025-10-15", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-1.6" }, { "id": "bytedance-seed/seed-1.6-flash", "label": "ByteDance Seed: Seed 1.6 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2025-08-28", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-1.6-flash" }, { "id": "bytedance-seed/seed-2-1-turbo", "label": "ByteDance Seed: Seed 2.1 Turbo", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-06-23", "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-2-1-turbo" }, { "id": "bytedance-seed/seed-2.0-code", "label": "ByteDance Seed: Seed-2.0-Code", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-14", "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-2.0-code" }, { "id": "bytedance-seed/seed-2.0-lite", "label": "ByteDance Seed: Seed-2.0-Lite", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-14", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-2.0-lite" }, { "id": "bytedance-seed/seed-2.0-mini", "label": "ByteDance Seed: Seed-2.0-Mini", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-14", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-2.0-mini" }, { "id": "bytedance/ui-tars-1.5-7b", "label": "ByteDance: UI-TARS 7B ", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 2048, "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-07-22", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/bytedance/ui-tars-1.5-7b" }, { "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition", "label": "Venice: Uncensored", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04-30", "releaseDate": "2025-07-09", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition" }, { "id": "cohere/command-a", "label": "Cohere: Command A", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8192, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cohere/command-a" }, { "id": "cohere/command-a-plus", "label": "Cohere: Command A+", "kind": "CHAT", "contextWindow": 192000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04-01", "releaseDate": "2026-05-20", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 6.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 223.97, "latencyTtftSec": 0.44, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cohere/command-a-plus" }, { "id": "cohere/command-r-08-2024", "label": "Cohere: Command R (08-2024)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-03-31", "releaseDate": "2024-08-30", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cohere/command-r-08-2024" }, { "id": "cohere/command-r-plus-08-2024", "label": "Cohere: Command R+ (08-2024)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-03-31", "releaseDate": "2024-08-30", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cohere/command-r-plus-08-2024" }, { "id": "cohere/command-r7b-12-2024", "label": "Cohere: Command R7B (12-2024)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2024-12-13", "pricing": { "inputPer1M": 0.0375, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cohere/command-r7b-12-2024" }, { "id": "cohere/north-mini-code:free", "label": "Cohere: North Mini Code (free)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-23", "releaseDate": "2026-06-09", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/cohere/north-mini-code:free" }, { "id": "deepseek/deepseek-chat", "label": "DeepSeek Chat (via OpenRouter)", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07-31", "releaseDate": "2025-12-01", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "openrouter-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-chat" }, { "id": "deepseek/deepseek-chat-v3-0324", "label": "DeepSeek: DeepSeek V3 0324", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07-31", "releaseDate": "2025-03-24", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-chat-v3-0324" }, { "id": "deepseek/deepseek-chat-v3.1", "label": "DeepSeek: DeepSeek V3.1", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 163840, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-21", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-chat-v3.1" }, { "id": "deepseek/deepseek-r1-0528", "label": "DeepSeek: R1 0528", "kind": "CHAT", "contextWindow": 65336, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-28", "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-r1-0528" }, { "id": "deepseek/deepseek-v3.1-terminus", "label": "DeepSeek: DeepSeek V3.1 Terminus", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-09-22", "pricing": { "inputPer1M": 0.27, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 13.9, "scores": { "math": { "value": 53.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 54.68, "latencyTtftSec": 0.74, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v3.1-terminus" }, { "id": "deepseek/deepseek-v3.2", "label": "DeepSeek: DeepSeek V3.2", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 163840, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07", "releaseDate": "2025-12-01", "pricing": { "inputPer1M": 0.28, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 16, "scores": { "math": { "value": 59 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v3.2" }, { "id": "deepseek/deepseek-v3.2-exp", "label": "DeepSeek: DeepSeek V3.2 Exp", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 163840, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v3.2-exp" }, { "id": "deepseek/deepseek-v4-flash", "label": "DeepSeek: DeepSeek V4 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 384000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "pricing": { "inputPer1M": 0.098, "outputPer1M": 0.196, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-flash" }, { "id": "deepseek/deepseek-v4-flash-0731", "label": "DeepSeek: DeepSeek V4 Flash 0731", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-07-31", "pricing": { "inputPer1M": 0.022, "outputPer1M": 0.32, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-flash-0731" }, { "id": "deepseek/deepseek-v4-flash-vision-exp", "label": "DeepSeek: DeepSeek V4 Flash Vision Exp", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-21", "pricing": { "inputPer1M": 0.22, "outputPer1M": 0.66, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-flash-vision-exp" }, { "id": "deepseek/deepseek-v4-pro", "label": "DeepSeek: DeepSeek V4 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 384000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "pricing": { "inputPer1M": 0.435, "outputPer1M": 0.87, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-pro" }, { "id": "deepseek/deepseek-v4-pro-0813", "label": "DeepSeek: DeepSeek V4 Pro 0813", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 384000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-13", "pricing": { "inputPer1M": 0.264, "outputPer1M": 0.792, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-pro-0813" }, { "id": "deepseek/deepseek-v4.1-flash", "label": "DeepSeek: DeepSeek V4.1 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 393216, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-09-10", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.42, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4.1-flash" }, { "id": "deepseek/deepseek-v4.1-flash-1017", "label": "DeepSeek: DeepSeek V4.1 Flash 1017", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 393216, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-10-17", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 32.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 163.217, "latencyTtftSec": 0.887, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4.1-flash-1017" }, { "id": "deepseek/deepseek-v4.1-flash:batch", "label": "DeepSeek: DeepSeek V4.1 Flash (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.112, "outputPer1M": 0.336, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4.1-flash:batch" }, { "id": "dots-studio/dots-3-note-preview:free", "label": "Dots Studio: Dots3-Note Preview (free)", "kind": "CHAT", "contextWindow": 512000, "maxOutputTokens": 460800, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-14", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/dots-studio/dots-3-note-preview:free" }, { "id": "elorian/glimpse", "label": "Elorian: Glimpse", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-17", "pricing": { "inputPer1M": 0.6, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/elorian/glimpse" }, { "id": "fireworks/ember-1", "label": "Fireworks: Ember-1", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/fireworks/ember-1" }, { "id": "google/gemini-2.0-flash-001", "label": "Gemini 2.0 Flash (via OpenRouter)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.0-flash-001" }, { "id": "google/gemini-2.5-flash", "label": "Google: Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-flash" }, { "id": "google/gemini-2.5-flash-image", "label": "Google: Nano Banana (Gemini 2.5 Flash Image)", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 8192, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-08-26", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-flash-image" }, { "id": "google/gemini-2.5-flash-lite", "label": "Google: Gemini 2.5 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-flash-lite" }, { "id": "google/gemini-2.5-pro", "label": "Google: Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-pro" }, { "id": "google/gemini-2.5-pro-preview", "label": "Google: Gemini 2.5 Pro Preview 06-05", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-06-05", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-pro-preview" }, { "id": "google/gemini-3-flash-preview", "label": "Google: Gemini 3 Flash Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-12-17", "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3-flash-preview" }, { "id": "google/gemini-3-flash-preview:batch", "label": "Google: Gemini 3 Flash Preview (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3-flash-preview:batch" }, { "id": "google/gemini-3-pro-image", "label": "Google: Nano Banana Pro (Gemini 3 Pro Image)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3-pro-image" }, { "id": "google/gemini-3-pro-image-preview", "label": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 32768, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-11-20", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3-pro-image-preview" }, { "id": "google/gemini-3.1-flash-image", "label": "Google: Nano Banana 2 (Gemini 3.1 Flash Image)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-image" }, { "id": "google/gemini-3.1-flash-image-preview", "label": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-26", "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-image-preview" }, { "id": "google/gemini-3.1-flash-lite", "label": "Google: Gemini 3.1 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-07", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-lite" }, { "id": "google/gemini-3.1-flash-lite-image", "label": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 66000, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-06-30", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-lite-image" }, { "id": "google/gemini-3.1-flash-lite-preview", "label": "Google: Gemini 3.1 Flash Lite Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-03", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-lite-preview" }, { "id": "google/gemini-3.1-flash-lite:batch", "label": "Google: Gemini 3.1 Flash Lite (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.125, "outputPer1M": 0.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-lite:batch" }, { "id": "google/gemini-3.1-pro-preview", "label": "Google: Gemini 3.1 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-pro-preview" }, { "id": "google/gemini-3.1-pro-preview-customtools", "label": "Google: Gemini 3.1 Pro Preview Custom Tools", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-pro-preview-customtools" }, { "id": "google/gemini-3.1-pro-preview:batch", "label": "Google: Gemini 3.1 Pro Preview (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-pro-preview:batch" }, { "id": "google/gemini-3.5-flash", "label": "Google: Gemini 3.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-05-19", "pricing": { "inputPer1M": 1.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.5-flash" }, { "id": "google/gemini-3.5-flash-lite", "label": "Google: Gemini 3.5 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-07-21", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.5-flash-lite" }, { "id": "google/gemini-3.5-flash-lite:batch", "label": "Google: Gemini 3.5 Flash Lite (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.5-flash-lite:batch" }, { "id": "google/gemini-3.5-flash:batch", "label": "Google: Gemini 3.5 Flash (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-01", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.5-flash:batch" }, { "id": "google/gemini-3.6-flash", "label": "Google: Gemini 3.6 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-07-21", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.6-flash" }, { "id": "google/gemini-3.6-flash:batch", "label": "Google: Gemini 3.6 Flash (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.375, "outputPer1M": 1.875, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.6-flash:batch" }, { "id": "google/gemini-3.7-flash", "label": "Google: Gemini 3.7 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-08-13", "pricing": { "inputPer1M": 0.75, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.7-flash" }, { "id": "google/gemini-3.7-flash:batch", "label": "Google: Gemini 3.7 Flash (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.375, "outputPer1M": 1.875, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.7-flash:batch" }, { "id": "google/gemini-3.8-flash", "label": "Google: Gemini 3.8 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 0.75, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.8-flash" }, { "id": "google/gemini-3.8-flash:batch", "label": "Google: Gemini 3.8 Flash (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.375, "outputPer1M": 1.875, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.8-flash:batch" }, { "id": "google/gemini-4-argon", "label": "Google: Gemini 4 Argon", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03", "releaseDate": "2026-10-13", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-4-argon" }, { "id": "google/gemini-4-argon:batch", "label": "Google: Gemini 4 Argon (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-4-argon:batch" }, { "id": "google/gemini-nano-banana-2.1", "label": "Google: Nano Banana 2.1", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 58982, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "releaseDate": "2026-10-06", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemini-nano-banana-2.1" }, { "id": "google/gemma-2-27b-it", "label": "Google: Gemma 2 27B", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 2048, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-07-13", "pricing": { "inputPer1M": 0.65, "outputPer1M": 0.65, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-2-27b-it" }, { "id": "google/gemma-3-12b-it", "label": "Google: Gemma 3 12B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-12", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-3-12b-it" }, { "id": "google/gemma-3-27b-it", "label": "Google: Gemma 3 27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-12", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.45, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-3-27b-it" }, { "id": "google/gemma-3-4b-it", "label": "Google: Gemma 3 4B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-12", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-3-4b-it" }, { "id": "google/gemma-4-26b-a4b-it", "label": "Google: Gemma 4 26B A4B ", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-02", "pricing": { "inputPer1M": 0.12, "outputPer1M": 0.35, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-26b-a4b-it" }, { "id": "google/gemma-4-26b-a4b-it:free", "label": "Google: Gemma 4 26B A4B (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-02", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-26b-a4b-it:free" }, { "id": "google/gemma-4-31b-it", "label": "Google: Gemma 4 31B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-31b-it" }, { "id": "google/gemma-4-31b-it:free", "label": "Google: Gemma 4 31B (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-31b-it:free" }, { "id": "google/lyria-3-clip-preview", "label": "Google: Lyria 3 Clip Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "releaseDate": "2026-03-25", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/lyria-3-clip-preview" }, { "id": "google/lyria-3-pro-preview", "label": "Google: Lyria 3 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "releaseDate": "2026-03-25", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/google/lyria-3-pro-preview" }, { "id": "gryphe/mythomax-l2-13b", "label": "MythoMax 13B", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-06-30", "releaseDate": "2023-08-10", "pricing": { "inputPer1M": 1.875, "outputPer1M": 1.875, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/gryphe/mythomax-l2-13b" }, { "id": "ibm-granite/granite-4.2-8b", "label": "IBM: Granite 4.2 8B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 117964, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-25", "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 5.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 58.55, "latencyTtftSec": 0.73, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/ibm-granite/granite-4.2-8b" }, { "id": "inception/mercury-2", "label": "Inception: Mercury 2", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 50000, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-24", "pricing": { "inputPer1M": 0.25, "outputPer1M": 0.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 13.8, "scores": { "coding": { "value": 31.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 514.07, "latencyTtftSec": 7.46, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inception/mercury-2" }, { "id": "inception/mercury-2.5", "label": "Inception: Mercury 2.5", "kind": "CHAT", "contextWindow": 260000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-08", "pricing": { "inputPer1M": 0.04, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 724.17, "latencyTtftSec": 3.03, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inception/mercury-2.5" }, { "id": "inception/mercury-3", "label": "Inception: Mercury 3", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-16", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.35, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inception/mercury-3" }, { "id": "inclusionai/ling-3.0-flash", "label": "inclusionAI: Ling 3.0 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-23", "pricing": { "inputPer1M": 0.021, "outputPer1M": 0.063, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 303.87, "latencyTtftSec": 1.71, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-3.0-flash" }, { "id": "inclusionai/ling-3.0-flash-vl", "label": "inclusionAI: Ling 3.0 Flash VL", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-10", "pricing": { "inputPer1M": 0.021, "outputPer1M": 0.0616, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-3.0-flash-vl" }, { "id": "inclusionai/ling-3.0-tiny", "label": "inclusionAI: Ling 3.0 Tiny", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 250000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-06", "pricing": { "inputPer1M": 0.015, "outputPer1M": 0.045, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-11-05" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-3.0-tiny" }, { "id": "inclusionai/ling-3.1-flash", "label": "inclusionAI: Ling 3.1 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-29", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.225, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 212.16, "latencyTtftSec": 1.75, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-3.1-flash" }, { "id": "inference-net/schematron-v2-small", "label": "Inference.net: Schematron V2 Small", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-16", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.23, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inference-net/schematron-v2-small" }, { "id": "inference-net/schematron-v2-turbo", "label": "Inference.net: Schematron V2 Turbo", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-16", "pricing": { "inputPer1M": 0.03, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/inference-net/schematron-v2-turbo" }, { "id": "liquid/lfm-2.5-2.6b", "label": "LiquidAI: LFM2.5-2.6B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-11", "pricing": { "inputPer1M": 0.35, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/liquid/lfm-2.5-2.6b" }, { "id": "liquid/lfm-2.5-2.6b:free", "label": "LiquidAI: LFM2.5-2.6B (free)", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-11", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/liquid/lfm-2.5-2.6b:free" }, { "id": "liquid/lfm-2.5-24b-a2b", "label": "LiquidAI: LFM2.5-24B-A2B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-13", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/liquid/lfm-2.5-24b-a2b" }, { "id": "mancer/weaver", "label": "Mancer: Weaver (alpha)", "kind": "CHAT", "contextWindow": 8000, "maxOutputTokens": 2000, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-06-30", "releaseDate": "2023-08-02", "pricing": { "inputPer1M": 5.625, "outputPer1M": 5.625, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mancer/weaver" }, { "id": "meituan/longcat-2.0", "label": "Meituan: LongCat 2.0", "kind": "CHAT", "contextWindow": 1048756, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-30", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 19.1, "scores": { "coding": { "value": 45.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 59.98, "latencyTtftSec": 2.77, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meituan/longcat-2.0" }, { "id": "meta-llama/llama-3-70b-instruct", "label": "Llama 3 70B Instruct (via OpenRouter)", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.59, "outputPer1M": 0.79, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 5.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 44.571, "latencyTtftSec": 0.614, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3-70b-instruct" }, { "id": "meta-llama/llama-3.1-70b-instruct", "label": "Meta: Llama 3.1 70B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-07-23", "pricing": { "inputPer1M": 0.4, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.6, "scores": { "math": { "value": 4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 18.86, "latencyTtftSec": 2.12, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.1-70b-instruct" }, { "id": "meta-llama/llama-3.1-8b-instruct", "label": "Meta: Llama 3.1 8B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-07-23", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.08, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.9, "scores": { "coding": { "value": 5.4 }, "math": { "value": 4.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 141.42, "latencyTtftSec": 0.91, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.1-8b-instruct" }, { "id": "meta-llama/llama-3.2-1b-instruct", "label": "Meta: Llama 3.2 1B Instruct", "kind": "CHAT", "contextWindow": 60000, "maxOutputTokens": 60000, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-09-25", "pricing": { "inputPer1M": 0.027, "outputPer1M": 0.201, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 4.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.2-1b-instruct" }, { "id": "meta-llama/llama-3.2-3b-instruct", "label": "Meta: Llama 3.2 3B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-09-25", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.33, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 5.7, "scores": { "math": { "value": 3.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.2-3b-instruct" }, { "id": "meta-llama/llama-3.3-70b-instruct", "label": "Meta: Llama 3.3 70B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-12-06", "pricing": { "inputPer1M": 0.13, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.7, "scores": { "coding": { "value": 11.9 }, "math": { "value": 7.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 86.9, "latencyTtftSec": 1.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.3-70b-instruct" }, { "id": "meta-llama/llama-4-maverick", "label": "Meta: Llama 4 Maverick", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-04-05", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 10, "scores": { "coding": { "value": 16.3 }, "math": { "value": 19.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 61.58, "latencyTtftSec": 0.99, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-4-maverick" }, { "id": "meta-llama/llama-4-scout", "label": "Meta: Llama 4 Scout", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-04-05", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 8.1, "scores": { "coding": { "value": 8.2 }, "math": { "value": 14 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 95.57, "latencyTtftSec": 0.83, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-4-scout" }, { "id": "meta-llama/llama-guard-4-12b", "label": "Meta: Llama Guard 4 12B", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 16384, "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-04-29", "pricing": { "inputPer1M": 0.18, "outputPer1M": 0.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-guard-4-12b" }, { "id": "meta/muse-glimmer-30b", "label": "Meta: Muse Glimmer 30B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-04", "releaseDate": "2026-08-10", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-glimmer-30b" }, { "id": "meta/muse-spark-1.1", "label": "Meta: Muse Spark 1.1", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-08", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.7, "scores": { "coding": { "value": 71.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 124.125, "latencyTtftSec": 0.925, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-1.1" }, { "id": "meta/muse-spark-1.2", "label": "Meta: Muse Spark 1.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-05", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-1.2" }, { "id": "meta/muse-spark-1.2-contributor", "label": "Meta: Muse Spark 1.2 Contributor", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-21", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-1.2-contributor" }, { "id": "meta/muse-spark-1.3", "label": "Meta: Muse Spark 1.3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 36.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-1.3" }, { "id": "meta/muse-spark-1.3-contributor", "label": "Meta: Muse Spark 1.3 Contributor", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-1.3-contributor" }, { "id": "meta/muse-spark-open", "label": "Meta: Muse Spark Open", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-01-04", "releaseDate": "2026-10-15", "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-open" }, { "id": "meta/muse-wonder", "label": "Meta: Muse Wonder", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-12", "pricing": { "inputPer1M": 4, "outputPer1M": 20, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 43.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 135.7, "latencyTtftSec": 44.95, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/meta/muse-wonder" }, { "id": "microsoft/phi-4", "label": "Microsoft: Phi 4", "kind": "CHAT", "contextWindow": 16384, "maxOutputTokens": 16384, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-01-10", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 5.9, "scores": { "math": { "value": 18 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 40.91, "latencyTtftSec": 2.58, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/microsoft/phi-4" }, { "id": "minimax/minimax-m1", "label": "MiniMax: MiniMax M1", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 40000, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m1" }, { "id": "minimax/minimax-m2.5", "label": "MiniMax: MiniMax M2.5", "kind": "CHAT", "contextWindow": 196608, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-12", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m2.5" }, { "id": "minimax/minimax-m2.7", "label": "MiniMax: MiniMax M2.7", "kind": "CHAT", "contextWindow": 204800, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-18", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m2.7" }, { "id": "minimax/minimax-m3", "label": "MiniMax: MiniMax M3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 512000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-06-01", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m3" }, { "id": "minimax/minimax-m3.1-flash", "label": "MiniMax: MiniMax M3.1 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 524288, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-19", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m3.1-flash" }, { "id": "mistralai/codestral-2508", "label": "Mistral: Codestral 2508", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 204800, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-07-30", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/codestral-2508" }, { "id": "mistralai/devstral-2512", "label": "Mistral: Devstral 2 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/devstral-2512" }, { "id": "mistralai/ministral-14b-2512", "label": "Mistral: Ministral 3 14B 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/ministral-14b-2512" }, { "id": "mistralai/ministral-3b-2512", "label": "Mistral: Ministral 3 3B 2512", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/ministral-3b-2512" }, { "id": "mistralai/ministral-8b-2512", "label": "Mistral: Ministral 3 8B 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/ministral-8b-2512" }, { "id": "mistralai/mistral-large", "label": "Mistral Large", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8191, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-11-30", "pricing": { "inputPer1M": 8, "outputPer1M": 24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large" }, { "id": "mistralai/mistral-large-2407", "label": "Mistral Large 2407", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 104857, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-03-31", "releaseDate": "2024-07-24", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large-2407" }, { "id": "mistralai/mistral-large-2512", "label": "Mistral: Mistral Large 3 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-11", "releaseDate": "2025-12-02", "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large-2512" }, { "id": "mistralai/mistral-large-4-0", "label": "Mistral: Mistral Large 4", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-06", "pricing": { "inputPer1M": 0.7, "outputPer1M": 2.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large-4-0" }, { "id": "mistralai/mistral-medium-3", "label": "Mistral: Mistral Medium 3", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 104857, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-07", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9, "scores": { "math": { "value": 30.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 44.72, "latencyTtftSec": 2.36, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3" }, { "id": "mistralai/mistral-medium-3-5", "label": "Mistral: Mistral Medium 3.5", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 209715, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-30", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3-5" }, { "id": "mistralai/mistral-medium-3-5:batch", "label": "Mistral: Mistral Medium 3.5 (batch)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 209715, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3-5:batch" }, { "id": "mistralai/mistral-medium-3.1", "label": "Mistral: Mistral Medium 3.1", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 104857, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-08-12", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9.2, "scores": { "coding": { "value": 20.5 }, "math": { "value": 38.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3.1" }, { "id": "mistralai/mistral-nemo", "label": "Mistral: Mistral Nemo", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-07-18", "pricing": { "inputPer1M": 0.019, "outputPer1M": 0.03, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-nemo" }, { "id": "mistralai/mistral-saba", "label": "Mistral: Saba", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 26214, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-02-17", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-saba" }, { "id": "mistralai/mistral-small-24b-instruct-2501", "label": "Mistral: Mistral Small 3", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 16384, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-01-30", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.08, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-small-24b-instruct-2501" }, { "id": "mistralai/mistral-small-2603", "label": "Mistral: Mistral Small 4", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 209715, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06", "releaseDate": "2026-03-16", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-small-2603" }, { "id": "mistralai/mistral-small-3.1-24b-instruct", "label": "Mistral: Mistral Small 3.1 24B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-03-17", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-small-3.1-24b-instruct" }, { "id": "mistralai/mistral-small-3.2-24b-instruct", "label": "Mistral: Mistral Small 3.2 24B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-06-20", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-small-3.2-24b-instruct" }, { "id": "mistralai/mixtral-8x22b-instruct", "label": "Mistral: Mixtral 8x22B Instruct", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-01-31", "releaseDate": "2024-04-17", "pricing": { "inputPer1M": 0.65, "outputPer1M": 0.65, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/mixtral-8x22b-instruct" }, { "id": "mistralai/voxtral-small-24b-2507", "label": "Mistral: Voxtral Small 24B 2507", "kind": "CHAT", "contextWindow": 32000, "maxOutputTokens": 26214, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "audio", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-15", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/mistralai/voxtral-small-24b-2507" }, { "id": "moondream/moondream3-preview", "label": "Moondream: Moondream 3 Preview", "kind": "CHAT", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-15", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moondream/moondream3-preview" }, { "id": "moondream/moondream3.1-9b-a2b", "label": "Moondream: Moondream 3.1", "kind": "CHAT", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-15", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moondream/moondream3.1-9b-a2b" }, { "id": "moonshotai/kimi-k2", "label": "MoonshotAI: Kimi K2 0711", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 100352, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "releaseDate": "2025-07-11", "pricing": { "inputPer1M": 0.57, "outputPer1M": 2.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 12.7, "scores": { "math": { "value": 57 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 43.68, "latencyTtftSec": 1.92, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2" }, { "id": "moonshotai/kimi-k2-0905", "label": "MoonshotAI: Kimi K2 0905", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 100352, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "releaseDate": "2025-09-05", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 15.3, "scores": { "math": { "value": 57.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 45.14, "latencyTtftSec": 1.76, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2-0905" }, { "id": "moonshotai/kimi-k2-thinking", "label": "MoonshotAI: Kimi K2 Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 100352, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08", "releaseDate": "2025-11-06", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 22, "scores": { "math": { "value": 94.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 108.29, "latencyTtftSec": 1.65, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2-thinking" }, { "id": "moonshotai/kimi-k2.5", "label": "MoonshotAI: Kimi K2.5", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-27", "pricing": { "inputPer1M": 0.6, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2.5" }, { "id": "moonshotai/kimi-k2.6", "label": "MoonshotAI: Kimi K2.6", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-20", "pricing": { "inputPer1M": 0.684, "outputPer1M": 3.42, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2.6" }, { "id": "moonshotai/kimi-k2.7-code", "label": "MoonshotAI: Kimi K2.7 Code", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "pricing": { "inputPer1M": 0.82, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2.7-code" }, { "id": "moonshotai/kimi-k3", "label": "MoonshotAI: Kimi K3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-07-16", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 43.6, "scores": { "coding": { "value": 76.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 36.808, "latencyTtftSec": 2.865, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k3" }, { "id": "moonshotai/kimi-k3:batch", "label": "MoonshotAI: Kimi K3 (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.28, "outputPer1M": 11.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k3:batch" }, { "id": "moonshotai/kimi-k3.1-pro", "label": "MoonshotAI: Kimi K3.1 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-23", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 46, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 30.997, "latencyTtftSec": 2.667, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k3.1-pro" }, { "id": "morph/morph-v3-fast", "label": "Morph: Morph V3 Fast", "kind": "CHAT", "contextWindow": 81920, "maxOutputTokens": 38000, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-07", "pricing": { "inputPer1M": 0.8, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/morph/morph-v3-fast" }, { "id": "morph/morph-v3-large", "label": "Morph: Morph V3 Large", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-07", "pricing": { "inputPer1M": 0.9, "outputPer1M": 1.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/morph/morph-v3-large" }, { "id": "nex-agi/nex-n2.5-mini", "label": "Nex AGI: Nex-N2.5-Mini", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-08", "pricing": { "inputPer1M": 0.025, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nex-agi/nex-n2.5-mini" }, { "id": "nex-agi/nex-n2.5-pro", "label": "Nex AGI: Nex-N2.5-Pro", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-08", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nex-agi/nex-n2.5-pro" }, { "id": "nousresearch/hermes-4-405b", "label": "Nous: Hermes 4 405B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 117964, "capabilities": [ "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-08-26", "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nousresearch/hermes-4-405b" }, { "id": "nvidia/nemotron-3-nano-30b-a3b", "label": "NVIDIA: Nemotron 3 Nano 30B A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 228000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-25", "releaseDate": "2025-12-15", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-nano-30b-a3b" }, { "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "label": "NVIDIA: Nemotron 3 Nano Omni (free)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-28", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free" }, { "id": "nvidia/nemotron-3-super-120b-a12b", "label": "NVIDIA: Nemotron 3 Super", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06", "releaseDate": "2026-03-11", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.45, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-super-120b-a12b" }, { "id": "nvidia/nemotron-3-ultra-550b-a55b", "label": "NVIDIA: Nemotron 3 Ultra", "kind": "CHAT", "contextWindow": 512288, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09", "releaseDate": "2026-06-04", "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-ultra-550b-a55b" }, { "id": "nvidia/nemotron-3-ultra-550b-a55b:free", "label": "NVIDIA: Nemotron 3 Ultra (free)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09", "releaseDate": "2026-06-04", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free" }, { "id": "nvidia/nemotron-3.5-content-safety", "label": "NVIDIA: Nemotron 3.5 Content Safety", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 117964, "capabilities": [ "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-02", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3.5-content-safety" }, { "id": "nvidia/nemotron-3.5-content-safety:free", "label": "NVIDIA: Nemotron 3.5 Content Safety (free)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "capabilities": [ "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-02", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3.5-content-safety:free" }, { "id": "nvidia/nemotron-3.5-lightning", "label": "NVIDIA: Nemotron 3.5 Lightning", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09", "releaseDate": "2026-08-11", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3.5-lightning" }, { "id": "nvidia/nemotron-3.5-lightning:free", "label": "NVIDIA: Nemotron 3.5 Lightning (free)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09", "releaseDate": "2026-08-11", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3.5-lightning:free" }, { "id": "nvidia/nemotron-3.5-super-vl", "label": "NVIDIA: Nemotron 3.5 Super VL", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-15", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 13.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 391.48, "latencyTtftSec": 0.72, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3.5-super-vl" }, { "id": "nvidia/nemotron-3.5-super-vl:free", "label": "NVIDIA: Nemotron 3.5 Super VL (free)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-10-15", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3.5-super-vl:free" }, { "id": "nvidia/switchyard", "label": "NVIDIA: Switchyard", "kind": "CHAT", "contextWindow": 1000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/nvidia/switchyard" }, { "id": "openai/gpt-3.5-turbo-0613", "label": "OpenAI: GPT-3.5 Turbo (older v0613)", "kind": "CHAT", "contextWindow": 4095, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "releaseDate": "2024-01-25", "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-3.5-turbo-0613" }, { "id": "openai/gpt-3.5-turbo-16k", "label": "OpenAI: GPT-3.5 Turbo 16k", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "releaseDate": "2023-08-28", "pricing": { "inputPer1M": 3, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-3.5-turbo-16k" }, { "id": "openai/gpt-4", "label": "OpenAI: GPT-4", "kind": "CHAT", "contextWindow": 8191, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "releaseDate": "2023-11-06", "pricing": { "inputPer1M": 30, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4" }, { "id": "openai/gpt-4-turbo:batch", "label": "OpenAI: GPT-4 Turbo (batch)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4-turbo:batch" }, { "id": "openai/gpt-4.1", "label": "OpenAI: GPT-4.1", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-04-14", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1" }, { "id": "openai/gpt-4.1-mini", "label": "OpenAI: GPT-4.1 Mini", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-04-14", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1-mini" }, { "id": "openai/gpt-4.1-mini:batch", "label": "OpenAI: GPT-4.1 Mini (batch)", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1-mini:batch" }, { "id": "openai/gpt-4.1-nano", "label": "OpenAI: GPT-4.1 Nano", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-04-14", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1-nano" }, { "id": "openai/gpt-4.1-nano:batch", "label": "OpenAI: GPT-4.1 Nano (batch)", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1-nano:batch" }, { "id": "openai/gpt-4.1:batch", "label": "OpenAI: GPT-4.1 (batch)", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 1, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1:batch" }, { "id": "openai/gpt-4o", "label": "GPT-4o (via OpenRouter)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-05-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "openrouter-api", "overrides" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o" }, { "id": "openai/gpt-4o-2024-05-13", "label": "OpenAI: GPT-4o (2024-05-13)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-05-13", "pricing": { "inputPer1M": 5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-2024-05-13" }, { "id": "openai/gpt-4o-2024-08-06", "label": "OpenAI: GPT-4o (2024-08-06)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-08-06", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-2024-08-06" }, { "id": "openai/gpt-4o-2024-11-20", "label": "OpenAI: GPT-4o (2024-11-20)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-11-20", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-2024-11-20" }, { "id": "openai/gpt-4o-mini", "label": "OpenAI: GPT-4o-mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-07-18", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-mini" }, { "id": "openai/gpt-4o-mini-2024-07-18", "label": "OpenAI: GPT-4o-mini (2024-07-18)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-07-18", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-mini-2024-07-18" }, { "id": "openai/gpt-4o-mini:batch", "label": "OpenAI: GPT-4o-mini (batch)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-mini:batch" }, { "id": "openai/gpt-4o:batch", "label": "OpenAI: GPT-4o (batch)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 1.25, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o:batch" }, { "id": "openai/gpt-5", "label": "OpenAI: GPT-5", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5" }, { "id": "openai/gpt-5-image", "label": "OpenAI: GPT-5 Image", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "knowledgeCutoff": "2024-10-01", "releaseDate": "2025-10-14", "pricing": { "inputPer1M": 10, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-image" }, { "id": "openai/gpt-5-image-mini", "label": "OpenAI: GPT-5 Image Mini", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "releaseDate": "2025-10-16", "pricing": { "inputPer1M": 2.5, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-image-mini" }, { "id": "openai/gpt-5-mini", "label": "OpenAI: GPT-5 Mini", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-31", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-mini" }, { "id": "openai/gpt-5-mini:batch", "label": "OpenAI: GPT-5 Mini (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-31", "pricing": { "inputPer1M": 0.125, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-mini:batch" }, { "id": "openai/gpt-5-nano", "label": "OpenAI: GPT-5 Nano", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-31", "releaseDate": "2025-08-07", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-nano" }, { "id": "openai/gpt-5-nano:batch", "label": "OpenAI: GPT-5 Nano (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-31", "pricing": { "inputPer1M": 0.025, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-nano:batch" }, { "id": "openai/gpt-5-pro", "label": "OpenAI: GPT-5 Pro", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-10-06", "pricing": { "inputPer1M": 15, "outputPer1M": 120, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-pro" }, { "id": "openai/gpt-5-pro:batch", "label": "OpenAI: GPT-5 Pro (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "pricing": { "inputPer1M": 7.5, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-pro:batch" }, { "id": "openai/gpt-5:batch", "label": "OpenAI: GPT-5 (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "pricing": { "inputPer1M": 0.625, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5:batch" }, { "id": "openai/gpt-5.1", "label": "OpenAI: GPT-5.1", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1" }, { "id": "openai/gpt-5.1-codex", "label": "OpenAI: GPT-5.1-Codex", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-codex" }, { "id": "openai/gpt-5.1-codex-max", "label": "OpenAI: GPT-5.1-Codex-Max", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-codex-max" }, { "id": "openai/gpt-5.1-codex-mini", "label": "OpenAI: GPT-5.1-Codex-Mini", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-codex-mini" }, { "id": "openai/gpt-5.1:batch", "label": "OpenAI: GPT-5.1 (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.625, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1:batch" }, { "id": "openai/gpt-5.2", "label": "OpenAI: GPT-5.2", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2" }, { "id": "openai/gpt-5.2-chat", "label": "OpenAI: GPT-5.2 Chat", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-chat" }, { "id": "openai/gpt-5.2-codex", "label": "OpenAI: GPT-5.2-Codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-codex" }, { "id": "openai/gpt-5.2-pro", "label": "OpenAI: GPT-5.2 Pro", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "pricing": { "inputPer1M": 21, "outputPer1M": 168, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-pro" }, { "id": "openai/gpt-5.2-pro:batch", "label": "OpenAI: GPT-5.2 Pro (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10.5, "outputPer1M": 84, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-pro:batch" }, { "id": "openai/gpt-5.2:batch", "label": "OpenAI: GPT-5.2 (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.875, "outputPer1M": 7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2:batch" }, { "id": "openai/gpt-5.3-codex", "label": "OpenAI: GPT-5.3-Codex", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.3-codex" }, { "id": "openai/gpt-5.4", "label": "OpenAI: GPT-5.4", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4" }, { "id": "openai/gpt-5.4-image-2", "label": "OpenAI: GPT-5.4 Image 2", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "releaseDate": "2026-04-21", "pricing": { "inputPer1M": 8, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-image-2" }, { "id": "openai/gpt-5.4-mini", "label": "OpenAI: GPT-5.4 Mini", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-mini" }, { "id": "openai/gpt-5.4-mini:batch", "label": "OpenAI: GPT-5.4 Mini (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "pricing": { "inputPer1M": 0.375, "outputPer1M": 2.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-mini:batch" }, { "id": "openai/gpt-5.4-nano", "label": "OpenAI: GPT-5.4 Nano", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-nano" }, { "id": "openai/gpt-5.4-nano:batch", "label": "OpenAI: GPT-5.4 Nano (batch)", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.625, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-nano:batch" }, { "id": "openai/gpt-5.4-pro", "label": "OpenAI: GPT-5.4 Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-pro" }, { "id": "openai/gpt-5.4-pro:batch", "label": "OpenAI: GPT-5.4 Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 90, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-pro:batch" }, { "id": "openai/gpt-5.4:batch", "label": "OpenAI: GPT-5.4 (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4:batch" }, { "id": "openai/gpt-5.5", "label": "OpenAI: GPT-5.5", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.5" }, { "id": "openai/gpt-5.5-pro", "label": "OpenAI: GPT-5.5 Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.5-pro" }, { "id": "openai/gpt-5.5-pro:batch", "label": "OpenAI: GPT-5.5 Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "pricing": { "inputPer1M": 15, "outputPer1M": 90, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.5-pro:batch" }, { "id": "openai/gpt-5.5:batch", "label": "OpenAI: GPT-5.5 (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.5:batch" }, { "id": "openai/gpt-5.6-luna", "label": "OpenAI: GPT-5.6 Luna", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-luna" }, { "id": "openai/gpt-5.6-luna-pro", "label": "OpenAI: GPT-5.6 Luna Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-luna-pro" }, { "id": "openai/gpt-5.6-luna-pro:batch", "label": "OpenAI: GPT-5.6 Luna Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-luna-pro:batch" }, { "id": "openai/gpt-5.6-luna:batch", "label": "OpenAI: GPT-5.6 Luna (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-luna:batch" }, { "id": "openai/gpt-5.6-sol", "label": "OpenAI: GPT-5.6 Sol", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-sol" }, { "id": "openai/gpt-5.6-sol-pro", "label": "OpenAI: GPT-5.6 Sol Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-sol-pro" }, { "id": "openai/gpt-5.6-sol-pro:batch", "label": "OpenAI: GPT-5.6 Sol Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-sol-pro:batch" }, { "id": "openai/gpt-5.6-sol:batch", "label": "OpenAI: GPT-5.6 Sol (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-sol:batch" }, { "id": "openai/gpt-5.6-terra", "label": "OpenAI: GPT-5.6 Terra", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-terra" }, { "id": "openai/gpt-5.6-terra-pro", "label": "OpenAI: GPT-5.6 Terra Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "releaseDate": "2026-07-09", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-terra-pro" }, { "id": "openai/gpt-5.6-terra-pro:batch", "label": "OpenAI: GPT-5.6 Terra Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-terra-pro:batch" }, { "id": "openai/gpt-5.6-terra:batch", "label": "OpenAI: GPT-5.6 Terra (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-terra:batch" }, { "id": "openai/gpt-6-astra", "label": "OpenAI: GPT-6 Astra", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-04-30", "releaseDate": "2026-09-04", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-astra" }, { "id": "openai/gpt-6-astra-pro", "label": "OpenAI: GPT-6 Astra Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-04", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-astra-pro" }, { "id": "openai/gpt-6-astra-pro:batch", "label": "OpenAI: GPT-6 Astra Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-astra-pro:batch" }, { "id": "openai/gpt-6-astra:batch", "label": "OpenAI: GPT-6 Astra (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-astra:batch" }, { "id": "openai/gpt-6-luna", "label": "OpenAI: GPT-6 Luna", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-05-18", "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-luna" }, { "id": "openai/gpt-6-luna-pro", "label": "OpenAI: GPT-6 Luna Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-luna-pro" }, { "id": "openai/gpt-6-luna-pro:batch", "label": "OpenAI: GPT-6 Luna Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-luna-pro:batch" }, { "id": "openai/gpt-6-luna:batch", "label": "OpenAI: GPT-6 Luna (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-luna:batch" }, { "id": "openai/gpt-6-sol", "label": "OpenAI: GPT-6 Sol", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-04-20", "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-sol" }, { "id": "openai/gpt-6-sol-pro", "label": "OpenAI: GPT-6 Sol Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-sol-pro" }, { "id": "openai/gpt-6-sol-pro:batch", "label": "OpenAI: GPT-6 Sol Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-sol-pro:batch" }, { "id": "openai/gpt-6-sol:batch", "label": "OpenAI: GPT-6 Sol (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6-sol:batch" }, { "id": "openai/gpt-6.1-sol", "label": "OpenAI: GPT-6.1 Sol", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-04-30", "releaseDate": "2026-09-29", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-sol" }, { "id": "openai/gpt-6.1-sol-pro", "label": "OpenAI: GPT-6.1 Sol Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-29", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-sol-pro" }, { "id": "openai/gpt-6.1-sol-pro:batch", "label": "OpenAI: GPT-6.1 Sol Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-sol-pro:batch" }, { "id": "openai/gpt-6.1-sol:batch", "label": "OpenAI: GPT-6.1 Sol (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-sol:batch" }, { "id": "openai/gpt-6.1-terra", "label": "OpenAI: GPT-6.1 Terra", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06-01", "releaseDate": "2026-10-26", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-terra" }, { "id": "openai/gpt-6.1-terra-pro", "label": "OpenAI: GPT-6.1 Terra Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-26", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-terra-pro" }, { "id": "openai/gpt-6.1-terra-pro:batch", "label": "OpenAI: GPT-6.1 Terra Pro (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-terra-pro:batch" }, { "id": "openai/gpt-6.1-terra:batch", "label": "OpenAI: GPT-6.1 Terra (batch)", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-6.1-terra:batch" }, { "id": "openai/gpt-audio", "label": "OpenAI: GPT Audio", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2023-10-01", "releaseDate": "2025-08-28", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-audio" }, { "id": "openai/gpt-audio-mini", "label": "OpenAI: GPT Audio Mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2023-10-01", "releaseDate": "2025-10-06", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-audio-mini" }, { "id": "openai/gpt-chat-latest", "label": "OpenAI: GPT Chat Latest", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-chat-latest" }, { "id": "openai/gpt-oss-120b", "label": "OpenAI: gpt-oss-120b", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 0.18, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-120b" }, { "id": "openai/gpt-oss-120b:batch", "label": "OpenAI: gpt-oss-120b (batch)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 117964, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.0296, "outputPer1M": 0.136, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-120b:batch" }, { "id": "openai/gpt-oss-20b", "label": "OpenAI: gpt-oss-20b", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 0.02, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-20b" }, { "id": "openai/gpt-oss-20b:batch", "label": "OpenAI: gpt-oss-20b (batch)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 117964, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.024, "outputPer1M": 0.112, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-20b:batch" }, { "id": "openai/gpt-oss-safeguard-20b", "label": "OpenAI: gpt-oss-safeguard-20b", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-10-29", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-safeguard-20b" }, { "id": "openai/o3", "label": "OpenAI: o3", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-04-16", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/o3" }, { "id": "openai/o3-mini:batch", "label": "OpenAI: o3 Mini (batch)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/o3-mini:batch" }, { "id": "openai/o3-pro", "label": "OpenAI: o3 Pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-06-10", "pricing": { "inputPer1M": 20, "outputPer1M": 80, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/o3-pro" }, { "id": "openai/o3:batch", "label": "OpenAI: o3 (batch)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 1, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/o3:batch" }, { "id": "openai/o4-mini:batch", "label": "OpenAI: o4 Mini (batch)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openai/o4-mini:batch" }, { "id": "openrouter/auto", "label": "Auto Router", "kind": "CHAT", "contextWindow": 2000000, "maxOutputTokens": 2000000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "releaseDate": "2023-11-08", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/auto" }, { "id": "openrouter/auto-beta", "label": "Auto Router (Beta)", "kind": "CHAT", "contextWindow": 2000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/auto-beta" }, { "id": "openrouter/auto-code", "label": "Auto Code", "kind": "CHAT", "contextWindow": 2000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/auto-code" }, { "id": "openrouter/bodybuilder", "label": "Body Builder (beta)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-05", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/bodybuilder" }, { "id": "openrouter/free", "label": "Free Models Router", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-01", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/free" }, { "id": "openrouter/fusion", "label": "OpenRouter: Fusion", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-13", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/fusion" }, { "id": "openrouter/pareto-code", "label": "Pareto Code Router", "kind": "CHAT", "contextWindow": 2000000, "maxOutputTokens": 200000, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-21", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/openrouter/pareto-code" }, { "id": "particle-ai/particle-1", "label": "Particle AI: Particle-1", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-28", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/particle-ai/particle-1" }, { "id": "perceptron/perceptron-mk1", "label": "Perceptron: Perceptron Mk1", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 8192, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-05-12", "pricing": { "inputPer1M": 0.15, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perceptron/perceptron-mk1" }, { "id": "perceptron/perceptron-mk1.5", "label": "Perceptron: Perceptron Mk1.5", "kind": "CHAT", "contextWindow": 36864, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-25", "pricing": { "inputPer1M": 0.15, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perceptron/perceptron-mk1.5" }, { "id": "perplexity/sonar", "label": "Perplexity: Sonar", "kind": "CHAT", "contextWindow": 127072, "maxOutputTokens": 114364, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-01-27", "pricing": { "inputPer1M": 1, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perplexity/sonar" }, { "id": "perplexity/sonar-deep-research", "label": "Perplexity: Sonar Deep Research", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 115200, "capabilities": [ "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-03-07", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perplexity/sonar-deep-research" }, { "id": "perplexity/sonar-pro", "label": "Perplexity: Sonar Pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8000, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-03-07", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perplexity/sonar-pro" }, { "id": "perplexity/sonar-pro-search", "label": "Perplexity: Sonar Pro Search", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8000, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-10-30", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perplexity/sonar-pro-search" }, { "id": "perplexity/sonar-reasoning-pro", "label": "Perplexity: Sonar Reasoning Pro", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 115200, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-03-07", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 11.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/perplexity/sonar-reasoning-pro" }, { "id": "prism-ml/ternary-bonsai-2-27b", "label": "PrismML: Ternary Bonsai 2 27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-18", "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/prism-ml/ternary-bonsai-2-27b" }, { "id": "prism-ml/ternary-bonsai-2-9b", "label": "PrismML: Ternary Bonsai 2 9B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-16", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.13, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/prism-ml/ternary-bonsai-2-9b" }, { "id": "qwen/qwen-2.5-72b-instruct", "label": "Qwen2.5 72B Instruct", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-09-19", "pricing": { "inputPer1M": 0.36, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.7, "scores": { "math": { "value": 14 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 28.09, "latencyTtftSec": 4.12, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-2.5-72b-instruct" }, { "id": "qwen/qwen-2.5-7b-instruct", "label": "Qwen: Qwen2.5 7B Instruct", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-10-16", "pricing": { "inputPer1M": 0.04, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-2.5-7b-instruct" }, { "id": "qwen/qwen-2.5-coder-32b-instruct", "label": "Qwen2.5 Coder 32B Instruct", "kind": "CHAT", "contextWindow": 33792, "maxOutputTokens": 33792, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-11-12", "pricing": { "inputPer1M": 0.18, "outputPer1M": 0.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-2.5-coder-32b-instruct" }, { "id": "qwen/qwen-plus", "label": "Qwen: Qwen-Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.26, "outputPer1M": 0.78, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-plus" }, { "id": "qwen/qwen2.5-vl-72b-instruct", "label": "Qwen: Qwen2.5 VL 72B Instruct", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-01-26", "pricing": { "inputPer1M": 0.8, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen2.5-vl-72b-instruct" }, { "id": "qwen/qwen3-14b", "label": "Qwen: Qwen3 14B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-04-28", "pricing": { "inputPer1M": 0.2275, "outputPer1M": 0.91, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-14b" }, { "id": "qwen/qwen3-235b-a22b-2507", "label": "Qwen: Qwen3 235B A22B Instruct 2507", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-21", "pricing": { "inputPer1M": 0.071, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-235b-a22b-2507" }, { "id": "qwen/qwen3-235b-a22b-thinking-2507", "label": "Qwen: Qwen3 235B A22B Thinking 2507", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-25", "pricing": { "inputPer1M": 0.11, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-235b-a22b-thinking-2507" }, { "id": "qwen/qwen3-30b-a3b", "label": "Qwen: Qwen3 30B A3B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-04-28", "pricing": { "inputPer1M": 0.13, "outputPer1M": 0.52, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-30b-a3b" }, { "id": "qwen/qwen3-30b-a3b-instruct-2507", "label": "Qwen: Qwen3 30B A3B Instruct 2507", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-30b-a3b-instruct-2507" }, { "id": "qwen/qwen3-32b", "label": "Qwen: Qwen3 32B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-04-28", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-32b" }, { "id": "qwen/qwen3-coder", "label": "Qwen: Qwen3 Coder 480B A35B", "kind": "CHAT", "contextWindow": 262100, "maxOutputTokens": 262100, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-22", "pricing": { "inputPer1M": 0.22, "outputPer1M": 0.95, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder" }, { "id": "qwen/qwen3-coder-30b-a3b-instruct", "label": "Qwen: Qwen3 Coder 30B A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-31", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.27, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9.6, "scores": { "math": { "value": 29 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-30b-a3b-instruct" }, { "id": "qwen/qwen3-coder-flash", "label": "Qwen: Qwen3 Coder Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.195, "outputPer1M": 0.975, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-flash" }, { "id": "qwen/qwen3-coder-next", "label": "Qwen: Qwen3 Coder Next", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09", "releaseDate": "2026-02-03", "pricing": { "inputPer1M": 0.11, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-next" }, { "id": "qwen/qwen3-next-80b-a3b-instruct", "label": "Qwen: Qwen3 Next 80B A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-30", "pricing": { "inputPer1M": 0.1, "outputPer1M": 1.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9.6, "scores": { "math": { "value": 66.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 124.786, "latencyTtftSec": 0.601, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-next-80b-a3b-instruct" }, { "id": "qwen/qwen3-vl-235b-a22b-instruct", "label": "Qwen: Qwen3 VL 235B A22B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-09-23", "pricing": { "inputPer1M": 0.21, "outputPer1M": 1.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9.9, "scores": { "math": { "value": 70.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 38.86, "latencyTtftSec": 1.23, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-235b-a22b-instruct" }, { "id": "qwen/qwen3-vl-30b-a3b-instruct", "label": "Qwen: Qwen3 VL 30B A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-10-04", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.9, "scores": { "math": { "value": 72.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 40.37, "latencyTtftSec": 2.66, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-30b-a3b-instruct" }, { "id": "qwen/qwen3-vl-30b-a3b-thinking", "label": "Qwen: Qwen3 VL 30B A3B Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-10-06", "pricing": { "inputPer1M": 0.13, "outputPer1M": 1.56, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-30b-a3b-thinking" }, { "id": "qwen/qwen3-vl-8b-instruct", "label": "Qwen: Qwen3 VL 8B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2025-10-14", "pricing": { "inputPer1M": 0.117, "outputPer1M": 0.455, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.3, "scores": { "math": { "value": 27.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-8b-instruct" }, { "id": "qwen/qwen3.5-122b-a10b", "label": "Qwen: Qwen3.5-122B-A10B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 15.6, "scores": { "coding": { "value": 45.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 133.727, "latencyTtftSec": 0.937, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-122b-a10b" }, { "id": "qwen/qwen3.5-27b", "label": "Qwen: Qwen3.5-27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 22.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-27b" }, { "id": "qwen/qwen3.5-35b-a3b", "label": "Qwen: Qwen3.5-35B-A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 19.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-35b-a3b" }, { "id": "qwen/qwen3.5-397b-a17b", "label": "Qwen: Qwen3.5 397B A17B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-15", "pricing": { "inputPer1M": 0.6, "outputPer1M": 3.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 18.4, "scores": { "coding": { "value": 48.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 58.8, "latencyTtftSec": 1.598, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-397b-a17b" }, { "id": "qwen/qwen3.5-9b", "label": "Qwen: Qwen3.5-9B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 13.7, "scores": { "coding": { "value": 28.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 64.17, "latencyTtftSec": 1.54, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-9b" }, { "id": "qwen/qwen3.5-flash-02-23", "label": "Qwen: Qwen3.5-Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-25", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-flash-02-23" }, { "id": "qwen/qwen3.5-plus-02-15", "label": "Qwen: Qwen3.5 Plus 2026-02-15", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-16", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-plus-02-15" }, { "id": "qwen/qwen3.5-plus-20260420", "label": "Qwen: Qwen3.5 Plus 2026-04-20", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-27", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-plus-20260420" }, { "id": "qwen/qwen3.6-27b", "label": "Qwen: Qwen3.6 27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262140, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-22", "pricing": { "inputPer1M": 0.288, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 21.4, "scores": { "coding": { "value": 53.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 58.427, "latencyTtftSec": 1.44, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-27b" }, { "id": "qwen/qwen3.6-35b-a3b", "label": "Qwen: Qwen3.6 35B A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-17", "pricing": { "inputPer1M": 0.14, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 18.2, "scores": { "coding": { "value": 41.9 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 136.722, "latencyTtftSec": 1.067, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-35b-a3b" }, { "id": "qwen/qwen3.6-flash", "label": "Qwen: Qwen3.6 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-27", "pricing": { "inputPer1M": 0.1875, "outputPer1M": 1.125, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-flash" }, { "id": "qwen/qwen3.6-plus", "label": "Qwen: Qwen3.6 Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-02", "pricing": { "inputPer1M": 0.325, "outputPer1M": 1.95, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 27, "scores": { "coding": { "value": 54.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 52.808, "latencyTtftSec": 1.638, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-plus" }, { "id": "qwen/qwen3.7-flash", "label": "Qwen: Qwen3.7 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-07-15", "pricing": { "inputPer1M": 0.03, "outputPer1M": 0.13, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.7-flash" }, { "id": "qwen/qwen3.7-max", "label": "Qwen: Qwen3.7 Max", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-21", "pricing": { "inputPer1M": 1.475, "outputPer1M": 4.425, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 29.5, "scores": { "coding": { "value": 66 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 199.573, "latencyTtftSec": 1.579, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.7-max" }, { "id": "qwen/qwen3.7-plus", "label": "Qwen: Qwen3.7 Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-06-02", "pricing": { "inputPer1M": 0.32, "outputPer1M": 1.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 25.2, "scores": { "coding": { "value": 55.9 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 54.825, "latencyTtftSec": 1.753, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.7-plus" }, { "id": "qwen/qwen3.7-plus:batch", "label": "Qwen: Qwen3.7 Plus (batch)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.23, "outputPer1M": 0.92, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.7-plus:batch" }, { "id": "qwen/qwen3.8-2.4t-a95b", "label": "Qwen: Qwen3.8 2.4T A95B", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-12", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 38.08, "latencyTtftSec": 3.13, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.8-2.4t-a95b" }, { "id": "qwen/qwen3.8-27b", "label": "Qwen: Qwen3.8 27B", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-14", "pricing": { "inputPer1M": 0.42, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 20.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 40.01, "latencyTtftSec": 4.03, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.8-27b" }, { "id": "qwen/qwen3.8-flash", "label": "Qwen: Qwen3.8 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-26", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.47, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.8-flash" }, { "id": "qwen/qwen3.8-max-0902", "label": "Qwen: Qwen3.8 Max (0902)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-02", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.8-max-0902" }, { "id": "qwen/qwen3.8-max-prime", "label": "Qwen: Qwen3.8 Max Prime", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-23", "pricing": { "inputPer1M": 4, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.8-max-prime" }, { "id": "qwen/qwen3.8-omni-flash", "label": "Qwen: Qwen3.8 Omni Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-17", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.47, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.8-omni-flash" }, { "id": "recursive/flint-v1.0:free", "label": "Recursive: Flint (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-21", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/recursive/flint-v1.0:free" }, { "id": "reflection/beam-1.0-501b-a23b", "label": "Reflection: Beam 1.0 501B A23B", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-06-30", "releaseDate": "2026-10-05", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/reflection/beam-1.0-501b-a23b" }, { "id": "rekaai/reka-edge", "label": "Reka Edge", "kind": "CHAT", "contextWindow": 16384, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-03-11", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/rekaai/reka-edge" }, { "id": "rekaai/reka-flash-3", "label": "Reka Flash 3", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-03-10", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 5.6, "scores": { "math": { "value": 33.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 90.05, "latencyTtftSec": 1.35, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/rekaai/reka-flash-3" }, { "id": "relace/relace-apply-3", "label": "Relace: Relace Apply 3", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 128000, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-09-26", "pricing": { "inputPer1M": 0.85, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/relace/relace-apply-3" }, { "id": "relace/relace-search", "label": "Relace: Relace Search", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-12-08", "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/relace/relace-search" }, { "id": "ricursiveai/ripple-65b-preview", "label": "ricursiveAI/Ripple-65B-Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-11-04", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-11-05" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/ricursiveai/ripple-65b-preview" }, { "id": "sakana/fugu-max", "label": "Sakana: Fugu Max", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-11", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/sakana/fugu-max" }, { "id": "sakana/fugu-ultra", "label": "Sakana: Fugu Ultra", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-15", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/sakana/fugu-ultra" }, { "id": "sakana/fugu-ultra-v2", "label": "Sakana: Fugu Ultra v2", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-08-28", "releaseDate": "2026-09-11", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/sakana/fugu-ultra-v2" }, { "id": "sakana/sakana-namazu", "label": "Sakana: Sakana Namazu", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-03", "pricing": { "inputPer1M": 0.95, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/sakana/sakana-namazu" }, { "id": "sao10k/l3-lunaris-8b", "label": "Sao10K: Llama 3 8B Lunaris", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-13", "pricing": { "inputPer1M": 0.04, "outputPer1M": 0.05, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/sao10k/l3-lunaris-8b" }, { "id": "sao10k/l3.1-euryale-70b", "label": "Sao10K: Llama 3.1 Euryale 70B v2.2", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-28", "pricing": { "inputPer1M": 0.85, "outputPer1M": 0.85, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/sao10k/l3.1-euryale-70b" }, { "id": "scaledown/extract", "label": "ScaleDown: Extract", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 900000, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-13", "pricing": { "inputPer1M": 0.04, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/scaledown/extract" }, { "id": "scaledown/summarize", "label": "ScaleDown: Summarize", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 4000, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-13", "pricing": { "inputPer1M": 0.04, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/scaledown/summarize" }, { "id": "stealth/crouton-alpha", "label": "Crouton Alpha", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-11-03", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/stealth/crouton-alpha" }, { "id": "stepfun/step-3.5-flash", "label": "StepFun: Step 3.5 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 17, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 294.218, "latencyTtftSec": 0.744, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/stepfun/step-3.5-flash" }, { "id": "stepfun/step-3.7-flash", "label": "StepFun: Step 3.7 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03-01", "releaseDate": "2026-05-29", "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 19.5, "scores": { "coding": { "value": 39.6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 188.801, "latencyTtftSec": 1.59, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/stepfun/step-3.7-flash" }, { "id": "stepfun/step-5-preview", "label": "StepFun: Step 5 Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-16", "pricing": { "inputPer1M": 1, "outputPer1M": 2.7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/stepfun/step-5-preview" }, { "id": "tencent/hunyuan-a13b-instruct", "label": "Tencent: Hunyuan A13B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-07-08", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.57, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hunyuan-a13b-instruct" }, { "id": "tencent/hy-mt2-1.8b", "label": "Tencent: Hy-MT2-1.8B", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-21", "pricing": { "inputPer1M": 0.044, "outputPer1M": 0.177, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy-mt2-1.8b" }, { "id": "tencent/hy-mt2-30b-a3b", "label": "Tencent: Hy-MT2-30B-A3B", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-21", "pricing": { "inputPer1M": 0.074, "outputPer1M": 0.295, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy-mt2-30b-a3b" }, { "id": "tencent/hy-mt2-7b", "label": "Tencent: Hy-MT2-7B", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-21", "pricing": { "inputPer1M": 0.074, "outputPer1M": 0.295, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy-mt2-7b" }, { "id": "tencent/hy3", "label": "Tencent: Hy3", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-06", "pricing": { "inputPer1M": 0.132, "outputPer1M": 0.528, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 25.3, "scores": { "coding": { "value": 58.8 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 79.12, "latencyTtftSec": 2.97, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy3" }, { "id": "tencent/hy3-preview", "label": "Tencent: Hy3 preview", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-20", "pricing": { "inputPer1M": 0.063, "outputPer1M": 0.21, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 22.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 113.227, "latencyTtftSec": 1.685, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy3-preview" }, { "id": "tencent/hy4", "label": "Tencent: Hy4", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-11-04", "pricing": { "inputPer1M": 0.417, "outputPer1M": 1.2505, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-11-05" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy4" }, { "id": "tencent/hy4-preview", "label": "Tencent: Hy4 preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-28", "pricing": { "inputPer1M": 0.834, "outputPer1M": 2.501, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/tencent/hy4-preview" }, { "id": "thedrummer/cydonia-24b-v4.1", "label": "TheDrummer: Cydonia 24B V4.1", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04-30", "releaseDate": "2025-09-27", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/thedrummer/cydonia-24b-v4.1" }, { "id": "thedrummer/skyfall-36b-v2", "label": "TheDrummer: Skyfall 36B V2", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-03-10", "pricing": { "inputPer1M": 0.55, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/thedrummer/skyfall-36b-v2" }, { "id": "thedrummer/unslopnemo-12b", "label": "TheDrummer: UnslopNemo 12B", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-11-08", "pricing": { "inputPer1M": 0.4, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/thedrummer/unslopnemo-12b" }, { "id": "thinkingmachines/inkling", "label": "Thinking Machines: Inkling", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 471859, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-15", "pricing": { "inputPer1M": 1, "outputPer1M": 4.05, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 12.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 176.39, "latencyTtftSec": 2.06, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/thinkingmachines/inkling" }, { "id": "thinkingmachines/inkling-small", "label": "Thinking Machines: Inkling Small", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-30", "pricing": { "inputPer1M": 0.45, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 12.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 181.36, "latencyTtftSec": 1.99, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/thinkingmachines/inkling-small" }, { "id": "typesafe/jev-router", "label": "TypeSafe: Jev Router", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/typesafe/jev-router" }, { "id": "unbiased/pareto-26.10", "label": "Pareto 26.10", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-15", "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/unbiased/pareto-26.10" }, { "id": "unbiased/pareto-26.9", "label": "Pareto 26.9", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-10-30" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/unbiased/pareto-26.9" }, { "id": "undi95/remm-slerp-l2-13b", "label": "ReMM SLERP 13B", "kind": "CHAT", "contextWindow": 6144, "maxOutputTokens": 4096, "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-06-30", "releaseDate": "2023-07-22", "pricing": { "inputPer1M": 1.875, "outputPer1M": 1.875, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/undi95/remm-slerp-l2-13b" }, { "id": "upstage/solar-mini4", "label": "Upstage: Solar Mini 4", "kind": "CHAT", "contextWindow": 524288, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02", "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 103.1, "latencyTtftSec": 1.87, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/upstage/solar-mini4" }, { "id": "upstage/solar-pro4", "label": "Upstage: Solar Pro 4", "kind": "CHAT", "contextWindow": 524288, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02", "releaseDate": "2026-08-06", "pricing": { "inputPer1M": 0.09, "outputPer1M": 0.36, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 86.11, "latencyTtftSec": 1.95, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/upstage/solar-pro4" }, { "id": "writer/palmyra-x5", "label": "Writer: Palmyra X5", "kind": "CHAT", "contextWindow": 1040000, "maxOutputTokens": 8192, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-04-28", "pricing": { "inputPer1M": 0.6, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/writer/palmyra-x5" }, { "id": "x-ai/grok-4.20", "label": "xAI: Grok 4.20", "kind": "CHAT", "contextWindow": 2000000, "maxOutputTokens": 1800000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-01", "releaseDate": "2026-03-31", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 25.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 112.88, "latencyTtftSec": 19.47, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.20" }, { "id": "x-ai/grok-4.20-multi-agent", "label": "xAI: Grok 4.20 Multi-Agent", "kind": "CHAT", "contextWindow": 2000000, "maxOutputTokens": 1800000, "capabilities": [ "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-01", "releaseDate": "2026-03-31", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.20-multi-agent" }, { "id": "x-ai/grok-4.3", "label": "xAI: Grok 4.3", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 900000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-17", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 24.9, "scores": { "coding": { "value": 42.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.3" }, { "id": "x-ai/grok-4.3:batch", "label": "SpaceXAI: Grok 4.3 (batch)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 900000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.3:batch" }, { "id": "x-ai/grok-4.5", "label": "xAI: Grok 4.5", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 450000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-08", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 38.8, "scores": { "coding": { "value": 72.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 55.991, "latencyTtftSec": 11.135, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.5" }, { "id": "x-ai/grok-4.6", "label": "SpaceXAI: Grok 4.6", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 450000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-01", "releaseDate": "2026-08-12", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.6" }, { "id": "x-ai/grok-4.6:batch", "label": "SpaceXAI: Grok 4.6 (batch)", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 450000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.6, "outputPer1M": 4.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-11-05" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.6:batch" }, { "id": "x-ai/grok-4.7", "label": "SpaceXAI: Grok 4.7", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 450000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-05", "releaseDate": "2026-09-21", "pricing": { "inputPer1M": 1.6, "outputPer1M": 4.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 34.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 85.579, "latencyTtftSec": 21.164, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-10-30" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.7" }, { "id": "x-ai/grok-4.7:batch", "label": "SpaceXAI: Grok 4.7 (batch)", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 450000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.6, "outputPer1M": 4.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-11-05" }, "sources": [ "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.7:batch" }, { "id": "x-ai/grok-build-0.1", "label": "xAI: Grok Build 0.1", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 230400, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-16", "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-build-0.1" }, { "id": "xiaomi/mimo-v2.5", "label": "Xiaomi: MiMo-V2.5", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.5" }, { "id": "xiaomi/mimo-v2.5-pro", "label": "Xiaomi: MiMo-V2.5-Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 26, "scores": { "coding": { "value": 60.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 51.76, "latencyTtftSec": 1.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.5-pro" }, { "id": "xiaomi/mimo-v2.6-flash", "label": "Xiaomi: MiMo-V2.6-Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 26.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 32.42, "latencyTtftSec": 3.22, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.6-flash" }, { "id": "xiaomi/mimo-v2.6-pro", "label": "Xiaomi: MiMo-V2.6-Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-22", "pricing": { "inputPer1M": 0.435, "outputPer1M": 0.87, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "benchmarks": { "intelligenceIndex": 29.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 41.08, "latencyTtftSec": 3.31, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.6-pro" }, { "id": "xiaomi/mimo-v2.6-pro-ultraspeed", "label": "Xiaomi: MiMo-V2.6-Pro-UltraSpeed", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-21", "pricing": { "inputPer1M": 4.35, "outputPer1M": 8.7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed" }, { "id": "xingchen-agi/xing4.0-29b-a4b:free", "label": "XingChen: Xing4.0 29B A4B (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 235929, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-10-16", "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/xingchen-agi/xing4.0-29b-a4b:free" }, { "id": "z-ai/glm-4.5", "label": "Z.ai: GLM 4.5", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 98304, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.5" }, { "id": "z-ai/glm-4.5-air", "label": "Z.ai: GLM 4.5 Air", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 98304, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.13, "outputPer1M": 0.85, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.5-air" }, { "id": "z-ai/glm-4.5v", "label": "Z.ai: GLM 4.5V", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "releaseDate": "2025-08-11", "pricing": { "inputPer1M": 0.6, "outputPer1M": 1.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.7, "scores": { "math": { "value": 15.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.5v" }, { "id": "z-ai/glm-4.6", "label": "Z.ai: GLM 4.6", "kind": "CHAT", "contextWindow": 202800, "maxOutputTokens": 131000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-09-30", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.6" }, { "id": "z-ai/glm-4.6v", "label": "Z.ai: GLM 4.6V", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-08", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 8.4, "scores": { "math": { "value": 26.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.6v" }, { "id": "z-ai/glm-4.7", "label": "Z.ai: GLM 4.7", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-22", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 22.2, "scores": { "coding": { "value": 45.3 }, "math": { "value": 95 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.7" }, { "id": "z-ai/glm-4.7-flash", "label": "Z.ai: GLM 4.7 Flash", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-19", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.7-flash" }, { "id": "z-ai/glm-5", "label": "Z.ai: GLM 5", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-12", "pricing": { "inputPer1M": 0.8, "outputPer1M": 2.56, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 27.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5" }, { "id": "z-ai/glm-5-turbo", "label": "Z.ai: GLM 5 Turbo", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-16", "pricing": { "inputPer1M": 1.2, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 26.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5-turbo" }, { "id": "z-ai/glm-5.1", "label": "Z.ai: GLM 5.1", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-07", "pricing": { "inputPer1M": 1.05, "outputPer1M": 3.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.1" }, { "id": "z-ai/glm-5.2", "label": "Z.ai: GLM 5.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-13", "pricing": { "inputPer1M": 0.791, "outputPer1M": 2.486, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.2" }, { "id": "z-ai/glm-5.3", "label": "Z.ai: GLM 5.3", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 943717, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-14", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3" }, { "id": "z-ai/glm-5.3-flash", "label": "Z.ai: GLM 5.3 Flash", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 943718, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-26", "pricing": { "inputPer1M": 0.045, "outputPer1M": 0.14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3-flash" }, { "id": "z-ai/glm-5.3-flash:batch", "label": "Z.ai: GLM 5.3 Flash (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3-flash:batch" }, { "id": "z-ai/glm-5.3-flashx", "label": "Z.ai: GLM 5.3 FlashX", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-18", "pricing": { "inputPer1M": 0.37, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3-flashx" }, { "id": "z-ai/glm-5.3-flashx-legal", "label": "Z.ai: GLM 5.3 FlashX Legal", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-11-02", "pricing": { "inputPer1M": 0.37, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-11-05" }, "sources": [ "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3-flashx-legal" }, { "id": "z-ai/glm-5.3-prime", "label": "Z.ai: GLM 5.3 Prime", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-09-23", "pricing": { "inputPer1M": 2.8, "outputPer1M": 8.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3-prime" }, { "id": "z-ai/glm-5.3:batch", "label": "Z.ai: GLM 5.3 (batch)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.45, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-09-26" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.3:batch" }, { "id": "z-ai/glm-5v-turbo", "label": "Z.ai: GLM 5V Turbo", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-01", "pricing": { "inputPer1M": 1.2, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 23.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "models-dev", "openrouter-api" ], "lastVerified": "2026-11-05", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5v-turbo" } ], "perplexity": [ { "id": "sonar", "label": "Sonar", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-01", "pricing": { "inputPer1M": 1, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "perplexity", "ref": "perplexity/sonar" }, { "id": "sonar-deep-research", "label": "Perplexity Sonar Deep Research", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32768, "capabilities": [ "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-02-01", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "perplexity", "ref": "perplexity/sonar-deep-research" }, { "id": "sonar-pro", "label": "Sonar Pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-01", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "perplexity", "ref": "perplexity/sonar-pro" }, { "id": "sonar-reasoning-pro", "label": "Sonar Reasoning Pro", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-01", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "perplexity", "ref": "perplexity/sonar-reasoning-pro" } ], "qwen": [ { "id": "deepseek-v4-flash-0731", "label": "DeepSeek V4 Flash 0731", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 393216, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-05", "releaseDate": "2026-07-31", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/deepseek-v4-flash-0731" }, { "id": "glm-5.2", "label": "GLM-5.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-13", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/glm-5.2" }, { "id": "kimi-k3", "label": "Kimi K3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 1048576, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-16", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/kimi-k3" }, { "id": "qvq-max", "label": "QVQ Max", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-03-25", "pricing": { "inputPer1M": 1.2, "outputPer1M": 4.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qvq-max" }, { "id": "qwen-coder", "label": "Qwen-Coder", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-coder" }, { "id": "qwen-flash", "label": "Qwen-Flash", "kind": "CHAT", "contextWindow": 997952, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-flash" }, { "id": "qwen-max", "label": "Qwen-Max", "kind": "CHAT", "contextWindow": 30720, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2024-04-03", "pricing": { "inputPer1M": 1.6, "outputPer1M": 6.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-max" }, { "id": "qwen-mt-plus", "label": "Qwen-MT Plus", "kind": "CHAT", "contextWindow": 16384, "maxOutputTokens": 8192, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "pricing": { "inputPer1M": 2.46, "outputPer1M": 7.37, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-mt-plus" }, { "id": "qwen-mt-turbo", "label": "Qwen-MT Turbo", "kind": "CHAT", "contextWindow": 16384, "maxOutputTokens": 8192, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "pricing": { "inputPer1M": 0.16, "outputPer1M": 0.49, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-mt-turbo" }, { "id": "qwen-omni-turbo", "label": "Qwen-Omni Turbo", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 2048, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-01-19", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.27, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-omni-turbo" }, { "id": "qwen-omni-turbo-realtime", "label": "Qwen-Omni Turbo Realtime", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 2048, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-05-08", "pricing": { "inputPer1M": 0.27, "outputPer1M": 1.07, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-omni-turbo-realtime" }, { "id": "qwen-plus", "label": "Qwen-Plus", "kind": "CHAT", "contextWindow": 129024, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-plus" }, { "id": "qwen-plus-character-ja", "label": "Qwen Plus Character (Japanese)", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 512, "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-plus-character-ja" }, { "id": "qwen-turbo", "label": "Qwen-Turbo", "kind": "CHAT", "contextWindow": 129024, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2024-11-01", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 6.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 107.358, "latencyTtftSec": 1.04, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-turbo" }, { "id": "qwen-vl-max", "label": "Qwen-VL Max", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2024-04-08", "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-vl-max" }, { "id": "qwen-vl-ocr", "label": "Qwen-VL OCR", "kind": "CHAT", "contextWindow": 34096, "maxOutputTokens": 4096, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2024-10-28", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-vl-ocr" }, { "id": "qwen-vl-plus", "label": "Qwen-VL Plus", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "pricing": { "inputPer1M": 0.21, "outputPer1M": 0.63, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-vl-plus" }, { "id": "qwen2-5-omni-7b", "label": "Qwen2.5-Omni 7B", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 2048, "capabilities": [ "tools", "vision" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-04", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen2-5-omni-7b" }, { "id": "qwen3-14b", "label": "Qwen3 14B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.35, "outputPer1M": 1.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-14b" }, { "id": "qwen3-235b-a22b", "label": "Qwen3 235B-A22B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.7, "outputPer1M": 2.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-235b-a22b" }, { "id": "qwen3-32b", "label": "Qwen3 32B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.7, "outputPer1M": 2.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-32b" }, { "id": "qwen3-8b", "label": "Qwen3 8B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.18, "outputPer1M": 0.7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-8b" }, { "id": "qwen3-coder-30b-a3b-instruct", "label": "Qwen3-Coder 30B-A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.45, "outputPer1M": 2.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 226.18, "latencyTtftSec": 1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-coder-30b-a3b-instruct" }, { "id": "qwen3-coder-480b-a35b-instruct", "label": "Qwen3-Coder 480B-A35B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 65.8, "latencyTtftSec": 1.14, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-coder-480b-a35b-instruct" }, { "id": "qwen3-coder-flash", "label": "Qwen3 Coder Flash", "kind": "CHAT", "contextWindow": 997952, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-coder-flash" }, { "id": "qwen3-coder-plus", "label": "Qwen3 Coder Plus", "kind": "CHAT", "contextWindow": 997952, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-23", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-coder-plus" }, { "id": "qwen3-livetranslate-flash-realtime", "label": "Qwen3-LiveTranslate Flash Realtime", "kind": "CHAT", "contextWindow": 53248, "maxOutputTokens": 4096, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-22", "pricing": { "inputPer1M": 10, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-livetranslate-flash-realtime" }, { "id": "qwen3-max", "label": "Qwen3 Max", "kind": "CHAT", "contextWindow": 258048, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-23", "pricing": { "inputPer1M": 1.2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-max" }, { "id": "qwen3-next-80b-a3b-instruct", "label": "Qwen3-Next 80B-A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.15, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 180.47, "latencyTtftSec": 0.85, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-next-80b-a3b-instruct" }, { "id": "qwen3-next-80b-a3b-thinking", "label": "Qwen3-Next 80B-A3B (Thinking)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.15, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-next-80b-a3b-thinking" }, { "id": "qwen3-omni-flash", "label": "Qwen3-Omni Flash", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-15", "pricing": { "inputPer1M": 0.43, "outputPer1M": 1.66, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-omni-flash" }, { "id": "qwen3-omni-flash-realtime", "label": "Qwen3-Omni Flash Realtime", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-15", "pricing": { "inputPer1M": 0.52, "outputPer1M": 1.99, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-omni-flash-realtime" }, { "id": "qwen3-vl-235b-a22b", "label": "Qwen3-VL 235B-A22B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.7, "outputPer1M": 2.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-vl-235b-a22b" }, { "id": "qwen3-vl-30b-a3b", "label": "Qwen3-VL 30B-A3B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-vl-30b-a3b" }, { "id": "qwen3-vl-plus", "label": "Qwen3-VL Plus", "kind": "CHAT", "contextWindow": 260096, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-23", "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-vl-plus" }, { "id": "qwen3.5-122b-a10b", "label": "Qwen3.5 122B-A10B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.4, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 127.51, "latencyTtftSec": 2.31, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.5-122b-a10b" }, { "id": "qwen3.5-27b", "label": "Qwen3.5 27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 75.94, "latencyTtftSec": 5.61, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.5-27b" }, { "id": "qwen3.5-35b-a3b", "label": "Qwen3.5 35B-A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 142.91, "latencyTtftSec": 2.01, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.5-35b-a3b" }, { "id": "qwen3.5-397b-a17b", "label": "Qwen3.5 397B-A17B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-15", "pricing": { "inputPer1M": 0.6, "outputPer1M": 3.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 59.06, "latencyTtftSec": 2.26, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.5-397b-a17b" }, { "id": "qwen3.5-flash", "label": "Qwen3.5 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-02-23", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.5-flash" }, { "id": "qwen3.5-plus", "label": "Qwen3.5 Plus", "kind": "CHAT", "contextWindow": 991808, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-16", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.5-plus" }, { "id": "qwen3.6-27b", "label": "Qwen3.6 27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-22", "pricing": { "inputPer1M": 0.6, "outputPer1M": 3.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 53.89, "latencyTtftSec": 3.61, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.6-27b" }, { "id": "qwen3.6-35b-a3b", "label": "Qwen3.6 35B-A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-17", "pricing": { "inputPer1M": 0.375, "outputPer1M": 2.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 126.05, "latencyTtftSec": 2.09, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.6-35b-a3b" }, { "id": "qwen3.6-flash", "label": "Qwen3.6 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-27", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.6-flash" }, { "id": "qwen3.6-max-preview", "label": "Qwen3.6 Max Preview", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-20", "pricing": { "inputPer1M": 1.3, "outputPer1M": 7.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.6-max-preview" }, { "id": "qwen3.6-plus", "label": "Qwen3.6 Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-02", "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 56.05, "latencyTtftSec": 2.02, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.6-plus" }, { "id": "qwen3.7-flash", "label": "Qwen3.7 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-07-15", "pricing": { "inputPer1M": 0.03, "outputPer1M": 0.13, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.7-flash" }, { "id": "qwen3.7-max", "label": "Qwen3.7 Max", "kind": "CHAT", "contextWindow": 991808, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-05-21", "pricing": { "inputPer1M": 2.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 199.38, "latencyTtftSec": 2.19, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.7-max" }, { "id": "qwen3.7-plus", "label": "Qwen3.7 Plus", "kind": "CHAT", "contextWindow": 991808, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-06-02", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 58.38, "latencyTtftSec": 2.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.7-plus" }, { "id": "qwen3.8-flash", "label": "Qwen3.8 Flash", "kind": "CHAT", "contextWindow": 991808, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-26", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.47, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.8-flash" }, { "id": "qwen3.8-max", "label": "Qwen3.8 Max", "kind": "CHAT", "contextWindow": 991808, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-03", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 33.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 37.55, "latencyTtftSec": 3.15, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.8-max" }, { "id": "qwen3.8-omni-flash", "label": "Qwen3.8 Omni Flash", "kind": "CHAT", "contextWindow": 991808, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-17", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.47, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3.8-omni-flash" }, { "id": "qwq-plus", "label": "QwQ Plus", "kind": "CHAT", "contextWindow": 98304, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-03-05", "pricing": { "inputPer1M": 0.8, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwq-plus" }, { "id": "qwen-image-2.0", "label": "qwen-image-2.0", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-image-2.0" }, { "id": "qwen-image-2.0-pro", "label": "qwen-image-2.0-pro", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-image-2.0-pro" }, { "id": "qwen-image-3.0", "label": "qwen-image-3.0", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-image-3.0" }, { "id": "qwen-image-3.0-pro", "label": "qwen-image-3.0-pro", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen-image-3.0-pro" }, { "id": "qwen3-asr-flash", "label": "Qwen3-ASR Flash", "kind": "TRANSCRIPTION", "contextWindow": 53248, "maxOutputTokens": 4096, "openWeights": false, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-08", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/qwen3-asr-flash" }, { "id": "happyhorse-1.0-i2v", "label": "happyhorse-1.0-i2v", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/happyhorse-1.0-i2v" }, { "id": "happyhorse-1.0-r2v", "label": "happyhorse-1.0-r2v", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/happyhorse-1.0-r2v" }, { "id": "happyhorse-1.0-t2v", "label": "happyhorse-1.0-t2v", "kind": "VIDEO", "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/happyhorse-1.0-t2v" }, { "id": "happyhorse-1.1-i2v", "label": "happyhorse-1.1-i2v", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/happyhorse-1.1-i2v" }, { "id": "happyhorse-1.1-r2v", "label": "happyhorse-1.1-r2v", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/happyhorse-1.1-r2v" }, { "id": "happyhorse-1.1-t2v", "label": "happyhorse-1.1-t2v", "kind": "VIDEO", "modalities": { "input": [ "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/happyhorse-1.1-t2v" }, { "id": "wan2.7-i2v", "label": "wan2.7-i2v", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/wan2.7-i2v" }, { "id": "wan2.7-r2v", "label": "wan2.7-r2v", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/wan2.7-r2v" }, { "id": "wan2.7-t2v", "label": "wan2.7-t2v", "kind": "VIDEO", "modalities": { "input": [ "audio", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/wan2.7-t2v" }, { "id": "wan3.0-video", "label": "wan3.0-video", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/wan3.0-video" }, { "id": "wan3.0-video-prime", "label": "wan3.0-video-prime", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "qwen", "ref": "qwen/wan3.0-video-prime" } ], "recraft": [ { "id": "recraftv2", "label": "recraftv2", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "recraft", "ref": "recraft/recraftv2" }, { "id": "recraftv3", "label": "recraftv3", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "recraft", "ref": "recraft/recraftv3" } ], "runway": [ { "id": "gen4_image", "label": "gen4_image", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/gen4_image" }, { "id": "gen4_image_turbo", "label": "gen4_image_turbo", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/gen4_image_turbo" }, { "id": "aleph2", "label": "aleph2", "kind": "VIDEO", "modalities": { "input": [ "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/aleph2" }, { "id": "gemini_omni_flash", "label": "gemini_omni_flash", "kind": "VIDEO", "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/gemini_omni_flash" }, { "id": "gen4_turbo", "label": "gen4_turbo", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/gen4_turbo" }, { "id": "gen4.5", "label": "gen4.5", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/gen4.5" }, { "id": "hailuo3", "label": "hailuo3", "kind": "VIDEO", "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/hailuo3" }, { "id": "seedance2", "label": "seedance2", "kind": "VIDEO", "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/seedance2" }, { "id": "seedance2_5", "label": "seedance2_5", "kind": "VIDEO", "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/seedance2_5" }, { "id": "seedance2_fast", "label": "seedance2_fast", "kind": "VIDEO", "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/seedance2_fast" }, { "id": "seedance2_mini", "label": "seedance2_mini", "kind": "VIDEO", "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/seedance2_mini" }, { "id": "veo3.1", "label": "veo3.1", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/veo3.1" }, { "id": "veo3.1_fast", "label": "veo3.1_fast", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "runway", "ref": "runway/veo3.1_fast" } ], "stability": [ { "id": "conservative", "label": "conservative", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/conservative" }, { "id": "creative", "label": "creative", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/creative" }, { "id": "erase", "label": "erase", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/erase" }, { "id": "fast", "label": "fast", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/fast" }, { "id": "inpaint", "label": "inpaint", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/inpaint" }, { "id": "outpaint", "label": "outpaint", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/outpaint" }, { "id": "remove-background", "label": "remove-background", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/remove-background" }, { "id": "replace-background-and-relight", "label": "replace-background-and-relight", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/replace-background-and-relight" }, { "id": "sd3", "label": "sd3", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3" }, { "id": "sd3-large", "label": "sd3-large", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3-large" }, { "id": "sd3-large-turbo", "label": "sd3-large-turbo", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3-large-turbo" }, { "id": "sd3-medium", "label": "sd3-medium", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3-medium" }, { "id": "sd3.5-large", "label": "sd3.5-large", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3.5-large" }, { "id": "sd3.5-large-turbo", "label": "sd3.5-large-turbo", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3.5-large-turbo" }, { "id": "sd3.5-medium", "label": "sd3.5-medium", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sd3.5-medium" }, { "id": "search-and-recolor", "label": "search-and-recolor", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/search-and-recolor" }, { "id": "search-and-replace", "label": "search-and-replace", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/search-and-replace" }, { "id": "sketch", "label": "sketch", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/sketch" }, { "id": "stable-image-core", "label": "stable-image-core", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/stable-image-core" }, { "id": "stable-image-ultra", "label": "stable-image-ultra", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/stable-image-ultra" }, { "id": "structure", "label": "structure", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/structure" }, { "id": "style", "label": "style", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/style" }, { "id": "style-transfer", "label": "style-transfer", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "stability", "ref": "stability/style-transfer" } ], "stepfun": [ { "id": "step-3.5-flash", "label": "Step 3.5 Flash", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "pricing": { "inputPer1M": 0.10461, "outputPer1M": 0.31384, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 115.15, "latencyTtftSec": 3.31, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/step-3.5-flash" }, { "id": "step-3.5-flash-2603", "label": "Step 3.5 Flash 2603", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "pricing": { "inputPer1M": 0.10461, "outputPer1M": 0.31384, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/step-3.5-flash-2603" }, { "id": "step-3.7-flash", "label": "Step 3.7 Flash", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-03-01", "releaseDate": "2026-05-29", "pricing": { "inputPer1M": 0.20175, "outputPer1M": 1.21052, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 82.84, "latencyTtftSec": 2.63, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/step-3.7-flash" }, { "id": "step-5-preview", "label": "Step 5 Preview", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-16", "pricing": { "inputPer1M": 1.04613, "outputPer1M": 2.98895, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/step-5-preview" }, { "id": "stepaudio-2.5-asr", "label": "StepAudio 2.5 ASR", "kind": "TRANSCRIPTION", "openWeights": false, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "releaseDate": "2026-04-24", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/stepaudio-2.5-asr" }, { "id": "step-tts-2", "label": "Step TTS 2", "kind": "SPEECH", "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "releaseDate": "2026-03-01", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/step-tts-2" }, { "id": "stepaudio-2.5-tts", "label": "StepAudio 2.5 TTS", "kind": "SPEECH", "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "releaseDate": "2026-04-16", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "stepfun", "ref": "stepfun/stepaudio-2.5-tts" } ], "together": [ { "id": "deepseek-ai/DeepSeek-R1", "label": "DeepSeek-R1", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 20480, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "pricing": { "inputPer1M": 3, "outputPer1M": 7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "together", "ref": "together/deepseek-ai/DeepSeek-R1" }, { "id": "deepseek-ai/DeepSeek-V3", "label": "DeepSeek-V3", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2024-12-26", "pricing": { "inputPer1M": 1.25, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.2, "scores": { "coding": { "value": 23 }, "math": { "value": 26 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "together", "ref": "together/deepseek-ai/DeepSeek-V3" }, { "id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "label": "Llama 3.3 70B Instruct Turbo", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "pricing": { "inputPer1M": 0.88, "outputPer1M": 0.88, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "together", "ref": "together/meta-llama/Llama-3.3-70B-Instruct-Turbo" }, { "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "label": "Llama 4 Maverick 17B", "kind": "CHAT", "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.27, "outputPer1M": 0.85, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "together", "ref": "together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" }, { "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "label": "Qwen3 235B A22B Instruct", "kind": "CHAT", "contextWindow": 262000, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-21", "pricing": { "inputPer1M": 0.2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "together", "ref": "together/Qwen/Qwen3-235B-A22B-Instruct-2507-tput" }, { "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "label": "Qwen3 Coder 480B", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-22", "pricing": { "inputPer1M": 2, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "together", "ref": "together/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8" } ], "vercel": [ { "id": "alibaba/qwen-3-235b", "label": "Qwen3 235B (via Vercel)", "kind": "CHAT", "contextWindow": 40960, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2025-07-21", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "vercel", "ref": "vercel/alibaba/qwen-3-235b" }, { "id": "amazon/nova-pro", "label": "Amazon Nova Pro (via Vercel)", "kind": "CHAT", "contextWindow": 300000, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7, "scores": { "math": { "value": 7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 131.45, "latencyTtftSec": 1.07, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "vercel", "ref": "vercel/amazon/nova-pro" }, { "id": "anthropic/claude-3.5-haiku", "label": "Claude 3.5 Haiku (via Vercel)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "vercel", "ref": "vercel/anthropic/claude-3.5-haiku" }, { "id": "cohere/command-a", "label": "Command A (via Vercel)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-13", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7.7, "scores": { "math": { "value": 13 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 55.482, "latencyTtftSec": 0.494, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "vercel", "ref": "vercel/cohere/command-a" }, { "id": "deepseek/deepseek-r1", "label": "DeepSeek-R1 (via Vercel)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "capabilities": [ "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.19, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "vercel", "ref": "vercel/deepseek/deepseek-r1" }, { "id": "google/gemini-2.0-flash", "label": "Gemini 2.0 Flash (via Vercel)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "vercel", "ref": "vercel/google/gemini-2.0-flash" } ], "vertex-ai": [ { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-11-05", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-1.5-pro" }, { "id": "gemini-2.0-flash", "label": "Gemini 2.0 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-2.0-flash" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-2.5-flash" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-2.5-pro" }, { "id": "text-embedding-005", "label": "text-embedding-005", "kind": "EMBEDDING", "contextWindow": 2048, "embeddingDimensions": 768, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "vertex-ai", "ref": "vertex-ai/text-embedding-005" } ], "volcengine": [ { "id": "doubao-seedance-2-0-260128", "label": "doubao-seedance-2-0-260128", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "volcengine", "ref": "volcengine/doubao-seedance-2-0-260128" }, { "id": "doubao-seedance-2-0-fast-260128", "label": "doubao-seedance-2-0-fast-260128", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "volcengine", "ref": "volcengine/doubao-seedance-2-0-fast-260128" }, { "id": "doubao-seedance-2-0-mini-260615", "label": "doubao-seedance-2-0-mini-260615", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "volcengine", "ref": "volcengine/doubao-seedance-2-0-mini-260615" }, { "id": "doubao-seedance-2-5-260628", "label": "doubao-seedance-2-5-260628", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "volcengine", "ref": "volcengine/doubao-seedance-2-5-260628" } ], "voyage": [ { "id": "voyage-3", "label": "voyage-3", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.06, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/voyage-3" }, { "id": "voyage-3-large", "label": "voyage-3-large", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/voyage-3-large" }, { "id": "voyage-3-lite", "label": "voyage-3-lite", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 512, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.02, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/voyage-3-lite" }, { "id": "voyage-code-3", "label": "voyage-code-3", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/voyage-code-3" }, { "id": "voyage-multimodal-3", "label": "voyage-multimodal-3", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "capabilities": [ "multimodal" ], "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/voyage-multimodal-3" }, { "id": "rerank-2", "label": "rerank-2", "kind": "RERANK", "contextWindow": 16000, "maxOutputTokens": 16000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/rerank-2" }, { "id": "rerank-2-lite", "label": "rerank-2-lite", "kind": "RERANK", "contextWindow": 8000, "maxOutputTokens": 8000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.02, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "voyage", "ref": "voyage/rerank-2-lite" } ], "xai": [ { "id": "grok-3", "label": "Grok 3", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 12.1, "scores": { "math": { "value": 58 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 79.32, "latencyTtftSec": 1.74, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-3" }, { "id": "grok-3-mini", "label": "Grok 3 Mini", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-3-mini" }, { "id": "grok-4", "label": "Grok 4", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 22.5, "scores": { "math": { "value": 92.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "performance": { "throughputTps": 71.64, "latencyTtftSec": 12.68, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "overrides" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4" }, { "id": "grok-4.20-0309-non-reasoning", "label": "Grok 4.20 (Non-Reasoning)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 1000000, "capabilities": [ "tools", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-09", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.20-0309-non-reasoning" }, { "id": "grok-4.20-0309-reasoning", "label": "Grok 4.20 (Reasoning)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 1000000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-09", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.20-0309-reasoning" }, { "id": "grok-4.20-multi-agent-0309", "label": "Grok 4.20 Multi-Agent", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 1000000, "capabilities": [ "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-09", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.20-multi-agent-0309" }, { "id": "grok-4.3", "label": "Grok 4.3", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 1000000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-17", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 84.94, "latencyTtftSec": 27.31, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.3" }, { "id": "grok-4.5", "label": "Grok 4.5", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 500000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-07-08", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 50.22, "latencyTtftSec": 13.46, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.5" }, { "id": "grok-4.6", "label": "Grok 4.6", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 500000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-01", "releaseDate": "2026-08-12", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 56.97, "latencyTtftSec": 37.01, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.6" }, { "id": "grok-4.7", "label": "Grok 4.7", "kind": "CHAT", "contextWindow": 500000, "maxOutputTokens": 500000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-05", "releaseDate": "2026-09-21", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 35.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 72.2, "latencyTtftSec": 102.56, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-4.7" }, { "id": "grok-build-0.1", "label": "Grok Build 0.1", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-16", "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-build-0.1" }, { "id": "grok-code-fast-1", "label": "Grok Code Fast 1", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning", "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.1, "scores": { "math": { "value": 43.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-code-fast-1" }, { "id": "1024-x-1024/grok-imagine-image-2.0", "label": "1024-x-1024/grok-imagine-image-2.0", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/1024-x-1024/grok-imagine-image-2.0" }, { "id": "grok-imagine-image", "label": "Grok Imagine Image", "kind": "IMAGE", "contextWindow": 16000, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "releaseDate": "2026-01-28", "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image" }, { "id": "grok-imagine-image-2.0", "label": "grok-imagine-image-2.0", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image-2.0" }, { "id": "grok-imagine-image-2026-03-02", "label": "grok-imagine-image-2026-03-02", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image-2026-03-02" }, { "id": "grok-imagine-image-pro", "label": "grok-imagine-image-pro", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image-pro" }, { "id": "grok-imagine-image-quality", "label": "Grok Imagine Image Quality", "kind": "IMAGE", "contextWindow": 16000, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "releaseDate": "2026-04-03", "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image-quality" }, { "id": "grok-imagine-image-quality-20260403", "label": "grok-imagine-image-quality-20260403", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image-quality-20260403" }, { "id": "grok-imagine-image-quality-latest", "label": "grok-imagine-image-quality-latest", "kind": "IMAGE", "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-image-quality-latest" }, { "id": "grok-imagine-video", "label": "Grok Imagine Video", "kind": "VIDEO", "contextWindow": 1024, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "releaseDate": "2026-01-28", "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-video" }, { "id": "grok-imagine-video-1.5", "label": "Grok Imagine Video 1.5", "kind": "VIDEO", "contextWindow": 1024, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "video" ] }, "releaseDate": "2026-05-30", "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-video-1.5" }, { "id": "grok-imagine-video-1.5-2026-05-30", "label": "grok-imagine-video-1.5-2026-05-30", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-video-1.5-2026-05-30" }, { "id": "grok-imagine-video-1.5-lite", "label": "Grok Imagine Video 1.5 Lite", "kind": "VIDEO", "contextWindow": 1024, "capabilities": [ "vision" ], "openWeights": false, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "releaseDate": "2026-10-01", "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-video-1.5-lite" }, { "id": "grok-imagine-video-1.5-preview", "label": "grok-imagine-video-1.5-preview", "kind": "VIDEO", "modalities": { "input": [ "audio", "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-11-05", "vendor": "xai", "ref": "xai/grok-imagine-video-1.5-preview" } ], "zai": [ { "id": "glm-4.5", "label": "GLM-4.5", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 355000000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 12.8, "scores": { "math": { "value": 73.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-09-26" }, "sources": [ "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.5" }, { "id": "glm-4.5-air", "label": "GLM-4.5-Air", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 106000000000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-28", "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 16.5, "scores": { "math": { "value": 80.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 82.56, "latencyTtftSec": 2.41, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.5-air" }, { "id": "glm-4.5-flash", "label": "GLM-4.5-Flash", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-28", "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.5-flash" }, { "id": "glm-4.5v", "label": "GLM-4.5V", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-08-11", "pricing": { "inputPer1M": 0.6, "outputPer1M": 1.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 66.4, "latencyTtftSec": 3.42, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.5v" }, { "id": "glm-4.6", "label": "GLM-4.6", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-30", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23, "scores": { "math": { "value": 44.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 33.9, "latencyTtftSec": 5.13, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "committed", "litellm", "models-dev", "overrides" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.6" }, { "id": "glm-4.6v", "label": "GLM-4.6V", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-08", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 74.57, "latencyTtftSec": 3.92, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.6v" }, { "id": "glm-4.6v-flash", "label": "GLM-4.6V-Flash", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2025-12-08", "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.6v-flash" }, { "id": "glm-4.7", "label": "GLM-4.7", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-22", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 37.22, "latencyTtftSec": 2.82, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.7" }, { "id": "glm-4.7-flash", "label": "GLM-4.7-Flash", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-19", "performance": { "throughputTps": 86.81, "latencyTtftSec": 1.13, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.7-flash" }, { "id": "glm-4.7-flashx", "label": "GLM-4.7-FlashX", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-19", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-4.7-flashx" }, { "id": "glm-5", "label": "GLM-5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-02-12", "pricing": { "inputPer1M": 1, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 52.1, "latencyTtftSec": 1.43, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5" }, { "id": "glm-5-turbo", "label": "GLM-5-Turbo", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-03-16", "pricing": { "inputPer1M": 1.2, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5-turbo" }, { "id": "glm-5.1", "label": "GLM-5.1", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-04-07", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 81.02, "latencyTtftSec": 1.33, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5.1" }, { "id": "glm-5.2", "label": "GLM-5.2", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-06-13", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "performance": { "throughputTps": 80.52, "latencyTtftSec": 1.64, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5.2" }, { "id": "glm-5.3", "label": "GLM-5.3", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "releaseDate": "2026-08-14", "pricing": { "inputPer1M": 1.4, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 31.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 73.91, "latencyTtftSec": 1.65, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5.3" }, { "id": "glm-5.3-flash", "label": "GLM-5.3-Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-08-26", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "benchmarks": { "intelligenceIndex": 27.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "performance": { "throughputTps": 66.56, "latencyTtftSec": 1.45, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-11-05" }, "sources": [ "artificial-analysis", "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5.3-flash" }, { "id": "glm-5.3-flashx", "label": "GLM-5.3-FlashX", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-09-18", "pricing": { "inputPer1M": 0.37, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "models-dev", "lastVerified": "2026-10-30" }, "sources": [ "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5.3-flashx" }, { "id": "glm-5v-turbo", "label": "GLM-5V-Turbo", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "releaseDate": "2026-04-01", "pricing": { "inputPer1M": 1.2, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-10-30" }, "sources": [ "litellm", "models-dev" ], "lastVerified": "2026-11-05", "vendor": "zai", "ref": "zai/glm-5v-turbo" } ] } }