Google: gemini-2.5-flash-lite API
The fastest and most cost-effective multimodal reasoning model in the Gemini 2.5 family. Optimized for high-throughput, low-latency tasks such as translation, classification, and real-time routing. As a "Thinking Model," it supports an optional reasoning budget, delivering logic superior to previous Flash generations at a fraction of the cost.
- 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: 2025-06-17
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of gemini-2.5-flash-lite?
gemini-2.5-flash-lite supports a context window of up to 1,048,576 tokens.
Does gemini-2.5-flash-lite support function calling?
Yes. gemini-2.5-flash-lite supports tool / function calling.
Does gemini-2.5-flash-lite support reasoning?
Yes. gemini-2.5-flash-lite is a reasoning-capable model.
What is the knowledge cutoff of gemini-2.5-flash-lite?
The knowledge cutoff of gemini-2.5-flash-lite is 2024-12-31.