Google: gemini-2.5-pro API
The flagship multimodal model of the Gemini 2.5 series. Featuring Adaptive Thinking, it dynamically scales reasoning depth based on task complexity. With a 1M token context window, it is the industry standard for autonomous coding, enterprise agent planning, and deep research involving massive datasets.
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input: text, image, audio, video, file
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-03-20
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of gemini-2.5-pro?
gemini-2.5-pro supports a context window of up to 1,048,576 tokens.
Does gemini-2.5-pro support function calling?
Yes. gemini-2.5-pro supports tool / function calling.
Does gemini-2.5-pro support reasoning?
Yes. gemini-2.5-pro is a reasoning-capable model.
What is the knowledge cutoff of gemini-2.5-pro?
The knowledge cutoff of gemini-2.5-pro is 2024-12-31.