AtlasAI Center AI tool intelligence
Search
Google · API model

Gemma 4 31B

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...

Context
262K
Input / 1M
$0.2
Output / 1M
$0.4
Downloads (30d)
9,502,198
Released
Apr 2, 2026
View on OpenRouterFind it in the catalog
Specifications

Gemma 4 31B specs

Provider
Google
Type
API model
Model ID
google/gemma-4-31b-it
Context window
262,144 tokens262K
Input price
$0.2per 1M input tokens
Output price
$0.4per 1M output tokens
Accepts
image, text, video
Produces
text
Task
image text to text
Released
Apr 2, 2026
License
apache-2.0
Base model
google/gemma-4-31B
Downloads
9,502,198Hugging Face, last 30 days
Likes
4,116
Popularity
36/100position #40 in OpenRouter's weekly usage ranking
Source
OpenRouter
Overview

About Gemma 4 31B

Gemma 4 31B is an API model from Google, released on Apr 2, 2026, with a context window of 262,144 tokens, pricing of $0.2 per million input tokens and $0.4 per million output tokens, the apache-2.0 license, 9,502,198 Hugging Face downloads in the last 30 days. It accepts image, text, video input and produces text output.

At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0024.

Specs are sourced from OpenRouter and were last checked on Nov 3, 2026. Always confirm current pricing and limits with the provider before production use.

Tool callingStructured outputsJSON modeReasoning
FAQ

Gemma 4 31B questions

What is the context window of Gemma 4 31B?

Gemma 4 31B supports a context window of 262,144 tokens.

How much does Gemma 4 31B cost?

Gemma 4 31B is listed at $0.2 per million input tokens and $0.4 per million output tokens on OpenRouter.

When was Gemma 4 31B released?

Gemma 4 31B was published on Apr 2, 2026.

What inputs does Gemma 4 31B accept?

Gemma 4 31B accepts image, text, video input and produces text output.