Gemma 4 31B
by Googletext+image+video->text14 endpoints
Neura Intelligence Index
66.4/ 100
Rank
#109—
Confidence
mediumBenchmarks
5(13% coverage)
Overview
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Capabilities
Text generation
Image understanding
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities
Modalities
Input
ImageTextVideo
Output
Text
Technical Specifications
Context Window
262.1K tokens
Max Output
16.4K tokens
Tokenizer
Gemma
Uptime (24h)
9986.4%
Parameters
30700000000B
License
apache_2_0Open Weights
Country
🇺🇸US
Release Date
April 2, 20265mo
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark Performance
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 84.3 | verified |
| Humanity's Last Exam | 26.5 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| MMMU-Pro | 76.9 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.09
Output$0.34
Cache read$0.05
Added
April 2, 2026
Last synced 9/18/2026