All Models
DeepSeek V4 Flash (New)
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 CrofAI | deepseek-v4-flash-0731 | $0.12/MTok | $0.21/MTok | 1M | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output