Model

Gemini 2.5 Flash-Lite (Non-thinking)

CLOSED

Google · Gemini 2.5 family · released Jun 17, 2025

Cheapest, fastest 2.5-tier model; thinking is off by default for lowest cost/latency.

ReasoningCodingVisionFunction callingTool useAgentic

1165.2

Elo · rank #199

Parameters

Undisclosed

Active params

Undisclosed

Context

1M tokens

Architecture

Sparse Mixture-of-Experts Transformer (natively multimodal)

License

Proprietary (Google API Terms)

Languages

—

API price (in/out)

$0.1 / $0.4

Modalities

text · vision · audio · video

Benchmark results

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

Aider PolyglotCoding26.7%#33

best: Claude Opus 4.5 · 89.4%

AIMEMath49.8%#118

best: GPT-5.2 · 100.0%

FACTS GroundingKnowledge84.1%#4

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

GPQA DiamondReasoning64.6%#157

best: GPT-6 Astra · 96.0%

Humanity's Last ExamReasoning5.1%#123

best: Claude Opus 5 · 64.7%

LiveCodeBenchCoding33.7%#145

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

MMLUKnowledge81.1%#81

best: OpenAI o3 · 92.9%

MMMUVision72.9%#43

best: Claude Fable 5 · 89.3%

SimpleQAKnowledge10.7%#35

best: GPT-4.5 · 62.5%

SWE-bench VerifiedCoding31.6%#114

best: Claude Opus 5 · 96.0%

Run it locally

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

Input / M tok

$0.1

Output / M tok

$0.4

Gemini 2.5 family

Elo progression across releases

Gemini 2.5 ProMar 20251839.1 Gemini 2.5 FlashMay 20251603.0 Gemini 2.5 Flash-Lite (Non-thinking)Jun 20251165.2 Gemini 2.5 Flash-Lite (Thinking)Jun 20251256.0

Resources

DOCSai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite APIAvailable via Google API

API price $0.1/$0.4 · each benchmark row carries its own source badge (see methodology)