Gemini 3.1 Flash Lite

google/gemini-3.1-flash-lite-20260507

Google's Gemini 3.1 Flash Lite is a multimodal model that accepts text, image, video, file, and audio inputs and generates text output. It provides a context length of 1,048,576 tokens, supports tool usage and reasoning capabilities, and is priced at $0.25 per million input tokens and $1.5 per million output tokens. The model is not open weights and was released on May 7 2026.

  • tool use
  • structured outputs
  • reasoning

At a glance

providergoogle
releasedMar 3, 2026
context1.0M
input / M$0.25

Specifications

What the API gives you

Context window
1.0M tokens
Max output
66K tokens
Input price
$0.25 / 1M tokens
Output price
$1.50 / 1M tokens
Cache read
$0.025 / 1M tokens
Modalities
text, image, video, file, audio → text
Knowledge cutoff
—
Released
Mar 3, 2026

Measured evidence

Public benchmark record

FrontierMath Tiers 1-3 (Epoch AI)‡
27.7% ± 2.72026-08-30high effort, evaluated 2026-08-30
FrontierMath Tiers 1-3 (Epoch AI)‡
21.4% ± 2.42026-08-28minimal effort, evaluated 2026-08-28
GPQA Diamond (Epoch AI)‡
81.8% ± 2.72026-08-06high effort, evaluated 2026-08-06
OTIS Mock AIME (Epoch AI)‡
80% ± 62026-08-06high effort, evaluated 2026-08-06

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Competition MathEstablished evidence

    30% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    24% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.