DeepSeek-V4.1-Flash is the lightweight flagship of DeepSeek's new architecture family, packing 552B total MoE parameters to deliver flagship-surpassing intelligence across key benchmarks, including out-performing DeepSeek-V4-Pro. It adopts a Causal Encoder-Decoder asymmetric design with 8B active parameters for input and 16B for output, and offers native multimodal visual understanding. KV Cache usage is cut to one-quarter of the previous generation's HBM and one-eighth of its SSD storage, dramatically lowering costs for long-context and agentic workloads. With a 1M-token context window and up to 384K-token maximum output, it balances high throughput, low latency, and exceptional cost efficiency.
Inference Service Provider
The inference service provider for deepseek-v4.1-flash is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text, Image | 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
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1000000 | Max Output Length | 393216 |
Context Window | 1000000 | Max Input Length (Thinking Mode) | 1000000 |
Max Output Length (Thinking Mode) | 393216 | Max Chain-of-Thought Length | 393216 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
Idle hours are 22:00–08:00 the next day (UTC+8); all other times are busy hours.
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input (Idle hours) | 0.141 | Per 1M tokens |
Input (Busy hours) | 0.283 | Per 1M tokens |
Output (Idle hours) | 0.565 | Per 1M tokens |
Output (Busy hours) | 1.131 | Per 1M tokens |
Input(Implicit Cache, Idle hours) | 0.014 | Per 1M tokens |
Input(Implicit Cache, Busy hours) | 0.028 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
- Germany (Frankfurt)
- US (Virginia)
- Japan (Tokyo)
- Hong Kong (China)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 15000 |
TPM (Tokens Per Minute) | 1,200,000 |