DeepSeek's experimental multimodal model. Matches DeepSeek V4 Flash on text — agentic use, reasoning and world knowledge — and adds image understanding, at V4 Flash pricing. Supports tool calling and thinking mode.
Model id — paste this in your code
deepseek/deepseek-v4-flash-vision-exp
Pricing · per 1M tokens
Show prices in
Input64.8 DA$0.259
Output194 DA$0.776
Cached input2.1 DA$0.0084
Context window1.05MMax output: 393K
Capabilities
Vision — Understands images and documents you send
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: