All Models
DeepSeek V4 Flash (Alibaba Cloud)
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Benchmarks
Available Providers (2)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 AIHubMix | alicloud-deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | 384K | |
 LLM Gateway | alibaba/deepseek-v4-flash | $0.20/MTok | $0.40/MTok | 1M | 393.2K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output