Google: Gemini 3 Flash Preview API
A high-speed, cost-efficient reasoning model from Google's Gemini 3 family. It features an adjustable "Thinking Level" architecture, delivering frontier-class logic and agentic coding capabilities at Flash-level latency. It excels in complex workflows while maintaining significant cost advantages.
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input: text, image, video, audio, file
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-12-17
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of Gemini 3 Flash Preview?
Gemini 3 Flash Preview supports a context window of up to 1,048,576 tokens.
Does Gemini 3 Flash Preview support function calling?
Yes. Gemini 3 Flash Preview supports tool / function calling.
Does Gemini 3 Flash Preview support reasoning?
Yes. Gemini 3 Flash Preview is a reasoning-capable model.
What is the knowledge cutoff of Gemini 3 Flash Preview?
The knowledge cutoff of Gemini 3 Flash Preview is 2024-12-31.