Try Gemini 3.1 Pro Preview in the Workbench
Run this model interactively, tune parameters, and compare outputs.
gemini-3-1-pro-preview
Gemini 3.1 Pro Preview is Google’s flagship multimodal reasoning model in the Gemini 3 series. It is built for complex, multi-step tasks where stronger planning, deeper synthesis, and reliable tool use are required.
Some other noteworthy features of Gemini 3.1 Pro Preview include improved token efficiency, structured outputs, function calling, code execution, search grounding, and support for multimodal inputs (text, image, video, audio, and PDF).
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Example request
Fetch model details
The models endpoint returns the full model object, including itsjson_request_schema.