Gemma 4 31B

Google

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.

Try Now

Capabilities

Thinking

Tool Use

Image Input

Example Use Cases

Multimodal reasoning with large context

Multilingual coding and document understanding

Technical Specifications

Context Window

262,144 tokens

Max Output

131,072 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.14

Non-Reasoning Output

$0.40

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.6 Plus