Google: Gemma 4 31B API
Gemma 4 31B IT is a multimodal dense model by Google DeepMind with 30.7B parameters. It supports text and image input with a 256K context window, configurable thinking mode, native function calling, and multilingual support in 140+ languages. Gemma 4 31B IT 是 Google DeepMind 开发的多模态密集模型，拥有 307 亿个参数。它支持文本和图像输入，上下文窗口大小为 256K，具有可配置的思维模式、原生函数调用以及对 140 多种语言的多语言支持。
- Context window: 262,000 tokens
- Max output: 16,400 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2026-04-01
Frequently Asked Questions
What is the context window of Gemma 4 31B?
Gemma 4 31B supports a context window of up to 262,000 tokens.
Does Gemma 4 31B support function calling?
Yes. Gemma 4 31B supports tool / function calling.
Does Gemma 4 31B support reasoning?
Yes. Gemma 4 31B is a reasoning-capable model.