M
Moonshot: kimi-k3
kimi-k3
1M context943.7K outReasoningToolsVisionVideoCacheStructured
Released Jul 16, 2026Knowledge cutoff Nov 2025Updated Aug 26, 2026
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.
Pricing
Input price
$0.06/ 1M tokens$3.0098% off
Output price
$0.28/ 1M tokens$15.0098% off
Compatible endpoints openaiVendor Moonshot
Uptime
Performance
Loading performance data...
Usage & Ranking
Loading usage...
Supported parameters
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 | All providers | Not sent by default |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| logprobs | All providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| presence_penalty | All providers | Not sent by default |
| reasoning | All providers | - |
| reasoning_effort | All providers | - |
| repetition_penalty | All providers | Not sent by default |
| response_format | All providers | - |
| seed | All providers | - |
| stop | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | Not sent by default |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | All providers | Not sent by default |
| top_logprobs | All providers | - |
| top_p | All providers | 0.95 |