Google: Gemini 3 Pro Preview API
Google's most intelligent and versatile flagship model in the Gemini 3 family. Designed for ultra-complex tasks, it features premier multimodal reasoning, PhD-level STEM problem-solving, and superior agentic performance. It is the first model to surpass 1500 Elo on LMArena.
- Context window: 1,000,000 tokens
- Max output: 64,000 tokens
- Input: text, image, video, audio, file
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-11-18
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of Gemini 3 Pro Preview?
Gemini 3 Pro Preview supports a context window of up to 1,000,000 tokens.
Does Gemini 3 Pro Preview support function calling?
Yes. Gemini 3 Pro Preview supports tool / function calling.
Does Gemini 3 Pro Preview support reasoning?
Yes. Gemini 3 Pro Preview is a reasoning-capable model.
What is the knowledge cutoff of Gemini 3 Pro Preview?
The knowledge cutoff of Gemini 3 Pro Preview is 2024-12-31.