Model

Gemini 2.0 Flash-Lite

CLOSED

Google · Gemini 2.0 family · released Feb 5, 2025

First Flash-Lite tier; single-rate pricing and cost-optimized successor to 1.5 Flash for large-scale text output.

ReasoningCodingVisionFunction callingTool useAgentic

1041.3

Elo · rank #216

Parameters

Undisclosed

Active params

Undisclosed

Context

1M tokens

Architecture

Sparse Mixture-of-Experts Transformer (params undisclosed), cost-optimized 2.0 tier

License

Proprietary

Languages

—

API price (in/out)

$0.075 / $0.3

Modalities

text · vision · audio · video

Benchmark results

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

Aider PolyglotCoding10.5%#39

best: Claude Opus 4.5 · 89.4%

AIMEMath23.8%#138

best: GPT-5.2 · 100.0%

BIRD-SQLCoding57.4%#4

best: Command A · 59.5%

FACTS GroundingKnowledge83.6%#5

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

GPQA DiamondReasoning51.5%#189

best: GPT-6 Astra · 96.0%

Humanity's Last ExamReasoning4.6%#130

best: Claude Opus 5 · 64.7%

LiveCodeBenchCoding28.9%#157

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

MATH-500Math86.8%#56

best: GPT-5 · 99.4%

MMLU-ProKnowledge71.6%#88

best: Claude Fable 5 · 91.5%

MMLUKnowledge78.0%#106

best: OpenAI o3 · 92.9%

MMMUVision68.0%#63

best: Claude Fable 5 · 89.3%

SimpleQAKnowledge21.7%#22

best: GPT-4.5 · 62.5%

SWE-bench VerifiedCoding12.5%#121

best: Claude Opus 5 · 96.0%

Run it locally

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

Input / M tok

$0.075

Output / M tok

$0.3

Gemini 2.0 family

Elo progression across releases

Gemini 2.0 FlashDec 20241312.1 Gemini 2.0 Flash Thinking (Experimental)Jan 20251521.9 Gemini 2.0 Flash-LiteFeb 20251041.3 Gemini 2.0 Pro ExperimentalFeb 20251344.8

Resources

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

API price $0.075/$0.3 · each benchmark row carries its own source badge (see methodology)