NanoGPT
DeepSeek V4 Flash Vision Exp
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
deepseek/deepseek-v4-flash-vision-expContext
1M
Max output
384K
Input $/M
$0.22
Output $/M
$0.66
Cache read $/M
$0.007
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 95% of the 7,784 models listed
Input price$0.22
Cheaper than 67% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturesupported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
TextImage
Output
Text
Reasoning controls
effortnone, low, high, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.22 |
| Output | $0.66 |
| Cache read | $0.007 |