Kimi-K3 is Moonshot AI's most capable flagship model to date, 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. As the world's first open-source model at the 3-trillion-parameter scale, it is designed for frontier intelligence scenarios such as long-horizon programming, knowledge work, and reasoning.
Inference Service Provider
The inference service provider for kimi-k3 is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
- Hong Kong (China)
Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Supported |
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 Model Studio console for promotional offers.
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
- Hong Kong (China)
Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 2.827 | Per 1M tokens |
Output | 14.133 | Per 1M tokens |
Input(Implicit Cache) | 0.283 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
- Hong Kong (China)
Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 15,000 |
TPM (Tokens Per Minute) | 1,200,000 |