DeepSeek's fast, cost-efficient general-purpose model with 1M context window, updated July 2026 with substantially enhanced agentic capabilities. Supports tool calling and thinking mode.
Model id — paste this in your code
deepseek/deepseek-v4-flash-0731
Pricing · per 1M tokens
Show prices in
Input22.8 DA$0.0912
Output45.9 DA$0.184
Cached input4.2 DA$0.0168
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: