DeepSeek: DeepSeek V4 Flash Vision Experimental
deepseek/deepseek-v4-flash-vision-exp
The deepseek-v4-flash-vision-exp model accepts images alongside text, so you can ask the model to describe pictures, read text from screenshots, analyze charts, and more. Supported image formats: JPEG, PNG, GIF, and WebP. The format is detected from the actual file content, not from the file name or the declared MIME type.
Model specifications
- Input
- text, image
- Output
- text
- Context
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Input price
- $0.44 / 1M tokens
- Output price
- $1.32 / 1M tokens
- Released
- 2026-08-21
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · tier input average $0.44 / 1M tokens · tier output average $1.32 / 1M tokens
DeepSeek
Tier: Standard · Region: CN
Pricing
- Input
- $0.44 / 1M tokens
- Output
- $1.32 / 1M tokens
- Cache read
- $0.014 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- CN
- Zero data retention
- Yes
- Data retention
- Unknown retention
- Used for training
- Yes
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Status · Support
Frequently asked questions
- What is DeepSeek: DeepSeek V4 Flash Vision Experimental?
- The deepseek-v4-flash-vision-exp model accepts images alongside text, so you can ask the model to describe pictures, read text from screenshots, analyze charts, and more. Supported image formats: JPEG, PNG, GIF, and WebP. The format is detected from the actual file content, not from the file name or the declared MIME type.
- How much does DeepSeek: DeepSeek V4 Flash Vision Experimental cost?
- Input costs start at $0.44 / 1M tokens and output costs start at $1.32 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of DeepSeek: DeepSeek V4 Flash Vision Experimental?
- DeepSeek: DeepSeek V4 Flash Vision Experimental supports a 1,048,576 token context window and up to 384,000 output tokens.
- What capabilities does DeepSeek: DeepSeek V4 Flash Vision Experimental support?
- DeepSeek: DeepSeek V4 Flash Vision Experimental supports Streaming, Function calling, Vision, JSON mode.
- Which providers offer DeepSeek: DeepSeek V4 Flash Vision Experimental?
- DeepSeek: DeepSeek V4 Flash Vision Experimental is available from DeepSeek.
- How do providers handle data privacy for DeepSeek: DeepSeek V4 Flash Vision Experimental?
- 1 of 1 providers report that customer data is not used for training, and 1 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.