DeepSeek V4 Flash Vision Exp
Weights availableDeepSeek V4 Flash Vision Exp weights published by DeepSeek in its Hugging Face organization (deepseek-ai/DeepSeek-V4-Flash-Vision-Exp). Self-hosting costs and serving limits depend on your deployment.
Access details: DeepSeek open weights (Hugging Face)
The Hugging Face repository. Download the weights and run them yourself or with a host.
deepseek-ai/DeepSeek-V4-Flash-Vision-ExpUpdated Oct 1, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- Not published
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Not published
Hosted price
USD / 1M tokens- Input
- $0.2156
- Output
- $0.6468
What OpenRouter charges for deepseek/deepseek-v4-flash-vision-exp. Other hosts set their own prices.
Free to download. Running the weights costs whatever your hardware or host charges.
Price history
Oct 1, 2026
Input Not applicable per million tokens
Oct 1, 2026
Output Not applicable per million tokens
Technical details
- Architecture
- V4-Flash architecture with added visual modules and continued training
- Input modalities
- Text, image
- Output modalities
- Text
License
MIT
From DeepSeek
Official announcement ↗How they describe it
our first experimental multimodal model in the DeepSeek-V4 family
What they say is new
Multimodality unlocks more agent use cases
Release & lifecycle
- Published
- Aug 31, 2026
- available
- As of Oct 1, 2026