Google: Gemini 3.1 Pro Preview API
Gemini 3.1 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 3.1 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, PDFs, and even entire code repositories with its 1M token context window. For more information on using the latest Gemini models, see Get started with Gemini 3. Quality improvements Gemini 3.1 Pro includes several quality improvements: Improved SWE and agentic capabilities: Improved software engineering behavior and usability, with agentic improvements in domains like finance and spreadsheet applications. Improved token efficiency and thinking: More efficient thinking across various use cases. Expanded thinking levels: Introduces MEDIUM as a thinking_level parameter for more options to optimize trade-offs between cost, performance, and speed.
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input: text, image, video, audio, file
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2026-02-19
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview supports a context window of up to 1,048,576 tokens.
Does Gemini 3.1 Pro Preview support function calling?
Yes. Gemini 3.1 Pro Preview supports tool / function calling.
Does Gemini 3.1 Pro Preview support reasoning?
Yes. Gemini 3.1 Pro Preview is a reasoning-capable model.
What is the knowledge cutoff of Gemini 3.1 Pro Preview?
The knowledge cutoff of Gemini 3.1 Pro Preview is 2024-12-31.