DeepSeek: DeepSeek V4 Flash Vision Exp
DeepSeek · Text
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
Model ID deepseek/deepseek-v4-flash-vision-expLegacyUpdated Sep 1, 2026
Pricing & billing
Billing unit: 1M tokens. Vendor reference price; conversion is approximate.
ItemUSD referenceList price (USD)
Input$0.15$0.15
Output$0.60$0.60
Cache read$0.003$0.003
Cache write—No public pricing—No public pricing
Specifications
- Form
- Text model
- Input modalities
- Text、Image
- Output modalities
- Text
- Context length
- 1M
- Max output
- 944K
- Weights
- Open weights
- Family
- deepseek-flash
- Released
- Aug 21, 2026
Uses and capabilities
Capabilities Text model、Function calling、Structured output、Reasoning、Prompt caching、Open weights
Function calling
Structured output
Reasoning
Prompt caching
Open weights
Sources
Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.