All Models
DeepSeek V4 Flash 0731 Cheaper (Thinking)
DeepSeek V4 Flash 0731 Cheaper Thinking enables reasoning by default on the same re-post-trained Mixture-of-Experts model with a 1M-token context window. This route goes directly to DeepSeek to use its lower cached-input pricing. ⚠️ Privacy and logging guarantees are limited.
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 NanoGPT | deepseek/deepseek-v4-flash-0731-cheaper:thinking | $0.14/MTok | $0.28/MTok | 1.0M | 384K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output