Gemma 4 31B IT

Gemma 4 31B IT is Google's largest instruction-tuned model in the Gemma line, designed for open, self-hosted chat and reasoning. It accepts image and text inputs and returns text, with a reasoning mode and tool calling. It has a 262,144-token context window and a 32,768-token output limit. Weights are open. Pricing starts at $0.09 per million input tokens and $0.25 per million output tokens, with cached input at $0.01 per million tokens. It is served by 35 hosts.

First version of its line in the registry.

Range across the hosts that serve it: up to $0.99 per 1M input tokens.

• ·262,144-token context window
• ·32,768-token max output
• ·Open weights for self-hosting
• ·Accepts image and text inputs
• ·Reasoning mode and tool calling

• Reach for it for self-hosted chat and reasoning
• Reach for it for processing long documents with a 262k context
• Reach for it for multimodal tasks combining image and text
• Reach for it for tool-calling workflows

35 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 262,144 tokens.

Are the weights open?

Yes, the weights are open for self-hosting.

What is the pricing?

From $0.09 per million input tokens and $0.25 per million output tokens, with cached input at $0.01 per million tokens.