All Models

Gemma 4 31B

gemma Reasoning Tool Calling Attachments Open Weights Structured Output

Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.

Providers 6
Released Apr 2, 2026
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

29.4
Intelligence Index
43.4
Coding Index

Available Providers (6)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Poe google/gemma-4-31b $0/MTok $0/MTok 262.1K 8.2K
Weights & Biases google/gemma-4-31B-it $0.10/MTok $0.34/MTok 262.1K 262.1K
NanoGPT google/gemma-4-31b-it $0.10/MTok $0.35/MTok 262.1K 131.1K
NovitaAI google/gemma-4-31b-it $0.14/MTok $0.40/MTok 262.1K 131.1K
Neuralwatt gemma-4-31b $0.14/MTok $0.42/MTok 262.1K 16.4K
NanoGPT TEE/gemma4-31b $0.45/MTok $1/MTok 262.1K 131.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output