DeepSeek-V3.2 is the official release of a model that incorporates DeepSeek Sparse Attention—a sparse attention mechanism. It’s also the first model launched by DeepSeek that integrates reasoning into tool usage, supporting both reasoning-enabled and non-reasoning tool calls.
Inference Service Provider
The inference service provider for deepseek-v3.2 is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Unsupported | Web Search | Supported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Supported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 98304 | Max Output Length | 65536 |
Context Window | 131072 |
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
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.287 | Per 1M tokens |
Output | 0.431 | Per 1M tokens |
Input(Implicit Cache) | 0.058 | Per 1M tokens |
Input(Batch File) | 0.144 | Per 1M tokens |
Output(Batch File) | 0.216 | Per 1M tokens |
Explicit Cache Creation | 0.359 | Per 1M tokens |
Explicit Cache Read | 0.029 | Per 1M tokens |
Input(Batch Chat) | 0.287 | Per 1M tokens |
Output(Batch Chat) | 0.431 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 15000 |
TPM (Tokens Per Minute) | 1,000,000 |