All Models
DeepSeek V4 Flash (Thinking)
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 NanoGPT | deepseek/deepseek-v4-flash:thinking | $0.07/MTok | $0.14/MTok | 1.0M | 384K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output