Gemma 4 31B

google • gemma-4-31b-it

Model Information

Slug	gemma-4-31b-it
LLM.txt	View
Release Date	April 2, 2026 New
HLE	0.265
GPQA	0.843

Organization

Name	google
Website	https://gemini.google.com/

Model Description

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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Available at 12 Providers

Provider	Type	Model Name	Original Model	Input ($/1M)	Output ($/1M)	Actions
Kilo Code	Code	Google: Gemma 4 31B	`google/gemma-4-31b-it`	$0.14	$0.40	Model
Novita AI		gemma-4-31b-it	`google/gemma-4-31b-it`	$0.14	$0.40	Visit
OpenRouter	Chat Code	Gemma 4 31B	`google/gemma-4-31b-it`	$0.14	$0.40	Model
Parasail		Gemma 4 31b It	`parasail-gemma-4-31b-it`	$0.14	$0.40	Model
AIHubMix		gemma-4-31b-it	`gemma-4-31b-it`	$0.14	$0.40	Model
GMI Cloud		Gemma 4 31B	`google/gemma-4-31b-it`	$0.14	$0.40	Visit
Fireworks AI		Gemma 4 31B IT	`gemma-4-31b-it`	$0.90	$0.90	Visit
Nano-GPT		Gemma 4 31B	`google/gemma-4-31b-it`	-	-	Visit
Nvidia		gemma-4-31b-it	`google/gemma-4-31b-it`	-	-	Model
Nano-GPT		Gemma 4 31B Thinking	`google/gemma-4-31b-it:thinking`	-	-	Visit
Writingmate	Chat Code	Google: Gemma 4 31B	`google/gemma-4-31b-it`	-	-	Model
OpenAdapter	Chat Code	openadapter	`gemma-4-31b-it`	-	-	Visit

Back to Models View Organization