Gemini 3.1 Pro

Gemini 3.1 Pro is Google’s preview Pro model for complex reasoning, software engineering and agentic workflows.

Gemini 3.1 Pro verified specifications

The API model code is gemini-3.1-pro-preview. Google documents a 1,048,576-token input limit, 65,536-token output limit and support for text, images, video, audio and PDFs.

Pricing and tools

Paid pricing begins at $2 per million input tokens and $12 per million output tokens for prompts up to 200K. Larger prompts cost $4/M input and $18/M output. The model supports thinking, function calling, structured outputs, code execution and search grounding.

Best uses

Gemini 3.1 Pro is best for complex coding, research synthesis, multimodal analysis and agents that need precise multi-step tool use.

Limitations

It remains a preview model, long-context requests cost more and production systems should monitor Google’s deprecation schedule.

Gemini 3.1 Pro capabilities and use cases

In addition, its main capabilities include 1M context, 65K output, Text image video audio PDF input, Thinking levels, Function calling and Code execution. For example, common use cases include Coding agents, Research synthesis, Document intelligence, Multimodal assistants and Complex planning.

Who should consider Gemini 3.1 Pro?

In practice, this model may suit Complex reasoning, Software engineering, Agentic workflows, Long-context research and Multimodal analysis. Also, notable strengths include Very large context, Broad multimodal support, Strong agent tools and Advanced reasoning. However, review trade-offs such as Preview behavior can change, Tool and grounding usage may add cost and Critical outputs need independent validation before adopting it.

Gemini 3.1 Pro pricing and access

Meanwhile, Gemini 3.1 Pro Preview costs $2/M input and $12/M output for prompts up to 200K tokens; above 200K, pricing rises to $4/M input and $18/M output. Pricing is tiered by prompt length. Long prompts above 200K tokens cost more, and grounding services can add separate charges.

Official resources and verification

Use the official model website, official documentation, pricing or release source and additional primary source to confirm current availability, limits and pricing. Product details can change after publication, so rely on primary documentation for final decisions.

Compare with other AI models

Next, continue your research in the AI models directory, Google models and Multimodal Language Model models. Compare providers, pricing, modalities and practical limitations side by side to choose the right model for your workflow.