Gemma 4 31Bon Krater.ai

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

Released April 2, 2026

Specifications

Gemma 4 31B at a glance

Context

262.1K tokens

Max output

262.1K tokens

Input

Image, Text, Video

Output

Text

Input price

$0.10 / 1M

Output price

$0.34 / 1M

Image inputTool callingStructured outputsReasoning support

Capabilities

What it is good at

Catalog capabilities

  • Accepts image input
  • Generates text responses
  • Supports tool calling
  • Supports structured outputs

Good for

Image understandingLong documentsUse with toolsStructured responsesDeep analysis

Benchmarks

Catalog data, not Krater benchmarks.

Coding index score

43.4

Agentic index score

14.4

Intelligence index score

29.7

FAQ

Questions about Gemma 4 31B

Clear answers based on the model catalog and Krater access.

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

Use Gemma 4 31B in your API

Connect with Krater's unified API.

API access

Ready to use Gemma 4 31B?

Access leading models in one focused workspace.