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.
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | Some providers | Not sent by default |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| logprobs | Some providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| presence_penalty | Some providers | Not sent by default |
| reasoning | All providers | - |
| reasoning_effort | All providers | - |
| repetition_penalty | Some providers | Not sent by default |
| response_format | Some providers | - |
| seed | Some providers | - |
| stop | Some providers | - |
| structured_outputs | Some providers | - |
| temperature | Some providers | Not sent by default |
| tool_choice | Some providers | - |
| tools | Some providers | - |
| top_k | Some providers | Not sent by default |
| top_logprobs | Some providers | - |
| top_p | Some providers | 0.95 |