Gemini 3.7 Flash is now available. Try it out.

Gemini 2.5 Pro

Our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.

Try in Google AI Studio

gemini-2.5-pro

Property	Description
Model code	`gemini-2.5-pro`
Supported data types	Inputs Audio, images, video, text, and PDF Output Text
Token limits^[*]	Input token limit 1,048,576 Output token limit 65,536
Capabilities	Audio generation Not supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported
Consumption options	Batch API Supported Flex inference Supported Priority inference Supported
Versions	Read the model version patterns for more details. `Stable: gemini-2.5-pro`
Latest update	June 2025
Knowledge cutoff	January 2025

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-06-23 UTC.