Model Catalog › gemini

Gemini 3.8 Flash

gemini-3.8-flash

CHAT Mid tier ReasoningMultimodal Proprietary (API-only)

Gemini 3.8 Flash (gemini-3.8-flash) is a chat model from gemini with a 1.0M-token context window; proprietary (API-only); capabilities tools, vision, reasoning; input audio, image, pdf, text, video; output text.

1.0MContext
65.5KMax output
$0.75$ / 1M in
30.8Intelligence
121.59tok / s

Pricing

Input
$0.75 / 1M tokens
Output
$3.75 / 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 2026-09-26.

Benchmarks

Intelligence index
30.8

Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-11-05.

Performance

Throughput
121.59 tokens/s
Latency (TTFT)
27.2 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-11-05.

Specifications

Context window
1,048,576 tokens (1.0M)
Max output
65,536 tokens
Weights
Proprietary (API-only)
Input modalities
audio image pdf text video
Output modalities
text
Release date
2026-09-02

Capabilities

tools vision reasoning

Provenance

artificial-analysisgemini-apilitellmmodels-dev
Last verified: 2026-11-05

Related models

Gemini 4 Argon
gemini-4-argon
gemini · CHAT · 1.0M ctx
Gemini 3.5 Flash
gemini-3.5-flash
gemini · CHAT · 1.0M ctx
Gemini 3.6 Flash
gemini-3.6-flash
gemini · CHAT · 1.0M ctx
Gemini 3.1 Pro Preview
gemini-3.1-pro-preview
gemini · CHAT · 1.0M ctx
Gemini 2.5 Pro
gemini-2.5-pro
gemini · CHAT · 1.0M ctx
Gemini 3.5 Flash Lite
gemini-3.5-flash-lite
gemini · CHAT · 1.0M ctx