Gemma 4 31B IT specs and limits

Google does not publish a public price for Gemma 4 31B IT, so the catalog shows no token cost for September 2026. Check the provider documentation for current terms: as soon as a price appears in the source feed, this card and its ruble conversion update automatically.

The Gemma 4 31B IT context window is 262K tokens (262,144). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Google model card as of September 2026.

The context window is 262K tokens (262,144) and a single response is capped at 33K tokens, so longer output has to be generated in parts. Rate limits are set by Google per account and depend on your plan rather than on the model, so they are not listed here.

Gemma 4 31B IT belongs to the Gemma (open weights) family at Google. Models in the Gemini line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Gemini model is listed on the provider page.

Yes, Gemma 4 31B IT declares a reasoning mode: it works through intermediate steps before it answers. Those steps add output tokens, so a call with a long reasoning chain costs more and takes longer than a plain completion. Capabilities declared for the model: reasoning, tool calling, image input, structured output.

The declared capabilities of Gemma 4 31B IT are: reasoning, tool calling, image input, structured output. It accepts text, images as input, and every attachment consumes tokens from the shared context window of 262K tokens. The list comes from the Google model card and is refreshed with the catalog as of September 2026.

Yes, Gemma 4 31B IT ships with open weights, so it can be downloaded and served on your own hardware instead of being used only through the Google API. What you may do with it is set by the license shown on the card. Catalog prices cover hosted API access.