Kimi-k2.5 is Moonshot AI's most versatile model with native multimodal architecture, supporting visual/text inputs, thinking/non-thinking modes, and both dialogue and agent tasks.
Inference Service Provider
The inference service provider for kimi-k2.5 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 229376 | Max Output Length | 16384 |
Context Window | 262144 |
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)
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.574 | Per 1M tokens |
Output | 3.011 | Per 1M tokens |
Input(Implicit Cache) | 0.115 | Per 1M tokens |
Explicit Cache Creation | 0.718 | Per 1M tokens |
Explicit Cache Read | 0.057 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 500 |
TPM (Tokens Per Minute) | 1,000,000 |