Kimi-K3 is Kimi's flagship model with 2.8 trillion parameters, built on the Kimi Delta Attention (KDA) hybrid linear attention mechanism and Attention Residuals. It natively supports visual understanding and a 1M-token context window, and targets long-horizon programming, knowledge work, and reasoning.
Inference Service Provider
The inference service provider for kimi/kimi-k3 is Moonshot AI.
Model Capabilities
- Singapore
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Unsupported |
Prefix Completion | Supported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
- Singapore
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1048576 | Max Output Length | 1048576 |
Context Window | 1000000 | 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
| 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
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 500 |
TPM (Tokens Per Minute) | 3,000,000 |