above.dev
DeepSeek V4 Flash Vision (Exp)
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
deepseek-v4-flash-vision-expContext
1M
Max output
384K
Input $/M
$0.24
Output $/M
$0.73
Cache read $/M
$0.0077
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 82% of the 7,784 models listed
Input price$0.24
Cheaper than 66% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturesupported
Open weightsnot supported
Interleaved thinkingsupported
Modalities
Input
TextImage
Output
Text
Reasoning controls
toggle—effortlow, high, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.24 |
| Output | $0.73 |
| Cache read | $0.0077 |
| Reasoning | $0.73 |