Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency. Note: reasoning effort currently supports only the max level (default); more levels are coming soon. See Moonshot AI's official docs here
所有提供方:为该模型提供服务的每个上游都支持。部分提供方:取决于处理请求的上游。默认值:未设置时发送的值。
| 参数 | 提供方 | 默认值 |
|---|---|---|
| frequency_penalty | 所有提供方 | 默认不发送 |
| include_reasoning | 所有提供方 | - |
| max_tokens | 所有提供方 | - |
| presence_penalty | 所有提供方 | 默认不发送 |
| reasoning | 所有提供方 | - |
| reasoning_effort | 所有提供方 | - |
| repetition_penalty | 部分提供方 | 默认不发送 |
| response_format | 所有提供方 | - |
| stop | 所有提供方 | - |
| structured_outputs | 所有提供方 | - |
| temperature | 部分提供方 | 默认不发送 |
| tool_choice | 所有提供方 | - |
| tools | 所有提供方 | - |
| top_k | 部分提供方 | 默认不发送 |
| top_p | 部分提供方 | 默认不发送 |