Model

Gemini 3.1 Flash-Lite

CLOSED

Google · Gemini 3.1 family · released Mar 3, 2026

Ultra-cheap 3.x tier for high-volume workloads at $0.25/$1.50 per million tokens, 1M context.

ReasoningCodingVisionFunction callingTool useAgentic

1920.1

Elo · rank #64

Parameters

Undisclosed

Active params

Undisclosed

Context

1M tokens

Architecture

Sparse Mixture-of-Experts Transformer (configuration undisclosed)

License

Proprietary

Languages

—

API price (in/out)

$0.25 / $1.5

Modalities

text · vision · audio · video

Benchmark results

Bar shows position within the tracked field; marker = field best

Arena EloHuman preference1432#13

best: Claude Fable 5 · 1505

CharXivVision73.2%#19

best: Muse Spark 1.1 (xhigh) · 88.4%

FACTS GroundingKnowledge40.6%#13

best: Gemini 2.5 Flash-Lite (Thinking) · 86.8%

GPQA DiamondReasoning86.9%#48

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning16.0%#71

best: Claude Sonnet 5 · 57.4%

LiveCodeBenchCoding72.0%#64

best: DeepSeek-V4-Pro (Think Max) · 93.5%

MMMLUKnowledge88.9%#11

best: Gemini 3.1 Pro · 92.6%

MMMU-ProVision76.8%#21

best: Claude Opus 4.7 · 85.5%

MMMUVision82.5%#17

best: Claude Fable 5 · 89.3%

SWE-bench VerifiedCoding62.8%#74

best: Claude Fable 5 · 95.0%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

$0.25

Output / M tok

$1.5

Gemini 3.1 family

Elo progression across releases

Gemini 3.1 ProFeb 20262598.4 Gemini 3.1 Flash-LiteMar 20261920.1

Resources

DOCShttps://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-flash-lite/APIAvailable via Google API

API price $0.25/$1.5 · each benchmark row carries its own source badge (see methodology)