Kimi-K3 is Moonshot AI's flagship model, featuring 2.8 trillion parameters. Built on the KDA hybrid linear attention mechanism (Kimi Delta Attention) and Attention Residuals, it natively supports visual understanding and offers a 1-million-token context window. It is designed for long-horizon programming, knowledge work, and reasoning.
Inference Service Provider
The inference service provider for kimi-k3 is QwenCloud.
Model Capabilities
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Unsupported |
Prefix Completion | Supported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1048576 | Max Output Length | 1048576 |
Context Window | 1048576 | Max Input Length (Thinking Mode) | 1048576 |
Max Output Length (Thinking Mode) | 1048576 | Max Chain-of-Thought Length | 1048576 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit QwenCloud console for promotional offers.
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 3 | Per 1M tokens |
Output | 15 | Per 1M tokens |
Input(Implicit Cache) | 0.3 | Per 1M tokens |
Rate Limits
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)