Context
1.0M
Input
$0.22/M
Output
$0.65/M
Aliases:deepseek-v4-flash-visiondeepseek-flash-visiondeepseek-visionds-v4-flash-vision
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.
deepinfra/deepseek-v4-flash-vision-expQuantfp8
- Input
- $0.22/M
- Output
- $0.65/M
- Context
- 1.0M
- Max out
- 262K
- Cache read
- $0.01/M
- Cache write
- $0.22/M
- Thinking out
- $0.65/M