DeepSeek-V4-Flash-0731 is an efficient lightweight MoE model with 284B total parameters and 13B activated parameters. It natively supports a 1M-token context window and is designed for everyday chat, content creation, basic RAG, and batch copywriting workloads.
Inference Service Provider
The inference service provider for deepseek-v4-flash-0731 is QwenCloud.
Model Capabilities
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Supported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Supported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1000000 | Max Output Length | 393216 |
Context Window | 1000000 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit QwenCloud console for promotional offers.
Off-peak hours are 22:00-08:00 UTC+8; all other hours are peak hours.
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input (off-peak) | 0.22 | Per 1M tokens |
Input (peak) | 0.44 | Per 1M tokens |
Output (off-peak) | 0.66 | Per 1M tokens |
Output (peak) | 1.32 | Per 1M tokens |
Input(Implicit Cache) (off-peak) | 0.022 | Per 1M tokens |
Input(Implicit Cache) (peak) | 0.044 | Per 1M tokens |
Rate Limits
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 15,000 |
TPM (Tokens Per Minute) | 1,200,000 |