# Google: Gemma 4 31B: AI model fact sheet

- **Provider:** google
- **Released:** 2026-04-02
- **Context window:** 262,144 tokens
- **API pricing:** $0.14 / 1M input, $0.40 / 1M output
- **OpenRouter ID:** google/gemma-4-31b-it
- **Capabilities:** conversation, reasoning, code-generation, analysis, function-calling

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.

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gemma-4-31b-it