kimi-k3 through MixRoute using the endpoint shown below.
Key capabilities
- 1M context window - Supports long-running work across large repositories and document sets
- Native multimodality - Understands text and image input
- Agentic workflows - Designed for coding, reasoning, and multi-step knowledge work
- OpenAI-compatible - Works with the OpenAI SDK by changing base_url
- Streaming - Real-time token output through SSE
Quick example
- cURL
- Python
- Streaming