Google: gemini-2.5-flash-lite-preview-09-2025 API
The most cost-effective lightweight reasoning model in the Gemini 2.5 family. The 09-2025 version introduces 2x token efficiency, designed for high-frequency, large-scale tasks with ultra-low latency. It supports native "Thinking" mode and features significant enhancements in instruction following, conciseness, and multimodal understanding.
- 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: 2025-09-25
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of gemini-2.5-flash-lite-preview-09-2025?
gemini-2.5-flash-lite-preview-09-2025 supports a context window of up to 1,048,576 tokens.
Does gemini-2.5-flash-lite-preview-09-2025 support function calling?
Yes. gemini-2.5-flash-lite-preview-09-2025 supports tool / function calling.
Does gemini-2.5-flash-lite-preview-09-2025 support reasoning?
Yes. gemini-2.5-flash-lite-preview-09-2025 is a reasoning-capable model.
What is the knowledge cutoff of gemini-2.5-flash-lite-preview-09-2025?
The knowledge cutoff of gemini-2.5-flash-lite-preview-09-2025 is 2024-12-31.