Moonshot: Kimi K3 API
Kimi K3 is Kimi's most powerful flagship model to date, boasting 2.8 trillion parameters. Built upon the KDA hybrid linear attention mechanism (Kimi Delta Attention) and attention residuals technology, it natively supports visual understanding and features a 1 million token context window. It is the world's first open-source model with over 3 trillion parameters, designed for cutting-edge intelligent scenarios such as long-range programming, knowledge work, and reasoning.
- Context window: 1,048,576 tokens
- Max output: 16,384 tokens
- Input: text, video, file, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2026-07-15
- Knowledge cutoff: 2025-11-30
Frequently Asked Questions
What is the context window of Kimi K3?
Kimi K3 supports a context window of up to 1,048,576 tokens.
Does Kimi K3 support function calling?
Yes. Kimi K3 supports tool / function calling.
Does Kimi K3 support reasoning?
Yes. Kimi K3 is a reasoning-capable model.
What is the knowledge cutoff of Kimi K3?
The knowledge cutoff of Kimi K3 is 2025-11-30.