Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is a reasoning-first Gemini preview from Google for agentic coding and complex problem solving. It sits in the gemini-pro line, succeeding Gemini 2.5 Computer Use Preview 10-2025. It has a context window of 1,048,576 tokens and a maximum output of 65,536 tokens. Pricing starts at $1.00 per million input tokens and $6.00 per million output tokens, with cached input at $0.10 per million tokens. The weights are not open. It supports reasoning mode, tool calling, and accepts audio, image, pdf, text, and video, returning text.

Against Gemini 2.5 Computer Use Preview 10-2025: window 128K to 1.05M, input $1.25 to $1.00, output $10.00 to $6.00.

Range across the hosts that serve it: up to $2.00 per 1M input tokens.

• ·1,048,576 token context window
• ·65,536 token maximum output
• ·Reasoning mode for complex problem solving
• ·Tool calling for agentic workflows
• ·Accepts audio, image, pdf, text, video

• Reach for it for agentic coding tasks
• Reach for it for complex problem solving
• Reach for it for handling long contexts up to 1M tokens
• Reach for it for multimodal input analysis

30 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 and output limit?

Context window is 1,048,576 tokens, max output is 65,536 tokens.

What is the pricing?

Input from $1.00 per million tokens, output $6.00 per million, cached input $0.10 per million.

Does it support tool calling and reasoning?

Yes, it has reasoning mode and tool calling.