DeepSeek's flagship reasoning model with 1M context window, updated to the DeepSeek-V4-Pro-0813 build served by DeepSeek's direct API. Supports tool calling, extended thinking, and high-quality generation.
Model id — paste this in your code
deepseek/deepseek-v4-pro-0813
Pricing · per 1M tokens
1 Pulse = 1 DA
Input238 Pulses= 238 DA
Output713 Pulses= 713 DA
Cached input7.92 Pulses= 7.92 DA
Context window1.05MMax output: 393K
Capabilities
Reasoning — Thinks step by step before answering
Tool use — Can call your functions / tools
Estimate your cost
Estimated cost
Use this model
Create an account, top up in dinars and call it with your key: