Google

Gemini 3.1 Flash Lite Preview

by Googletext+image+file+audio+video->text3 endpoints
Neura Intelligence Index
57.5/ 100
Rank
#151
Confidence
medium
Benchmarks
7(18% coverage)

Overview

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

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
Deterministic seed

Modalities

Input
TextImageVideoFileAudio
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
65.5K tokens
Tokenizer
Gemini
Uptime (24h)
9999.6%
Country
🇺🇸US
Release Date
March 3, 20266mo

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p

Benchmark Performance

general

BenchmarkScoreSource
MMMLU
88.9
verified
MRCR v2
60.1
verified
SimpleQA
43.3
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
86.9
verified
Humanity's Last Exam
16
verified

multimodal

BenchmarkScoreSource
MMMU-Pro
76.8
verified
CharXiv Reasoning
73.2
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.25
Output$1.50
Cache read$0.03
Cache write$0.08
Audio$0.50
Reasoning$1.50
Image$0.25
Added
March 3, 2026
Last synced 9/20/2026