DeepSeek-V3.2 harmonizes high computational efficiency with superior reasoning and agent performance. Built on DeepSeek-V3, it incorporates key innovations like DeepSeek Sparse Attention (DSA), scalable reinforcement learning frameworks, and large-scale agent task synthesis pipelines, advancing the frontier of open-source LLMs.
Inference Service Provider
The inference service provider for vanchin/deepseek-v3.2-think is Kuaishou Vanchin.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | 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
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 98304 | Max Output Length | 65536 |
Context Window | 131072 | Max Input Length (Thinking Mode) | 98304 |
Max Output Length (Thinking Mode) | 65536 |
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)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Input | 2 | Per 1M tokens |
Output | 3 | Per 1M tokens |
Input(Implicit Cache) | 0.2 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 30 |
TPM (Tokens Per Minute) | 600,000 |