Google: gemini-2.5-flash API
The "Price-Performance King" of the Gemini 2.5 family. It is the first lightweight model to combine high throughput and low latency with native reasoning (Thinking) capabilities. It handles up to 1M context tokens and can tackle complex logic—tasks previously reserved for Pro models—via a configurable "Thinking Budget."
- 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-flash?
gemini-2.5-flash supports a context window of up to 1,048,576 tokens.
Does gemini-2.5-flash support function calling?
Yes. gemini-2.5-flash supports tool / function calling.
Does gemini-2.5-flash support reasoning?
Yes. gemini-2.5-flash is a reasoning-capable model.
What is the knowledge cutoff of gemini-2.5-flash?
The knowledge cutoff of gemini-2.5-flash is 2024-12-31.