All Models

Gemma 4 31B

gemma Reasoning Tool Calling Attachments Open Weights Structured Output

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...

Providers 4
Released Apr 2, 2026
Input Modalities text, image, video
Output Modalities text
Tarsk Use coding

Benchmarks

39.2
Intelligence Index
38.7
Coding Index

Available Providers (4)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Poe google/gemma-4-31b $0.00/MTok $0.00/MTok 262.1K 8.2K
OpenRouter google/gemma-4-31b-it $0.14/MTok $0.40/MTok 262.1K 262.1K
NovitaAI google/gemma-4-31b-it $0.14/MTok $0.40/MTok 262.1K 131.1K
Google gemma-4-31b-it —/MTok —/MTok 256K 8.2K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output