GPT-4.1 (gpt-4.1) is a chat model from openai with a 1.0M-token context window; proprietary (API-only); capabilities vision, tools; input image, pdf, text; output text.
1.0MContext
32.8KMax output
$2$ / 1M in
151.52tok / s
Pricing
Input
$2 / 1M tokens
Output
$8 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.
Performance
Throughput
151.52 tokens/s
Latency (TTFT)
1.09 s
Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-11-05.