Google

Gemini 2.5 Flash Lite

by Googletext+image+file+audio+video->text5 endpoints
Neura Intelligence Index
18.8/ 100
Rank
#296
Confidence
medium
Benchmarks
6(15% coverage)

Overview

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

Capabilities

Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
TextImageFileAudioVideo
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
65.5K tokens
Knowledge Cutoff
2025-01-31
Tokenizer
Gemini
Uptime (24h)
10000.0%
License
creative_commons_attribution_4_0_licenseOpen Weights
Country
🇺🇸US
Release Date
June 17, 20251y

Supported Parameters

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Benchmark Performance

general

BenchmarkScoreSource
SimpleQA
10.7
verified

coding

BenchmarkScoreSource
SWE-bench Verified
31.6
verified

math

BenchmarkScoreSource
AIME 2025
49.8
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
64.6
verified
Humanity's Last Exam
5.1
verified

multimodal

BenchmarkScoreSource
MMMU
72.9
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.10
Output$0.40
Cache read$0.01
Cache write$0.08
Audio$0.30
Reasoning$0.40
Image$0.10
Added
July 22, 2025
Last synced 9/18/2026