AMD
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
$0.14
Output $/M
$0.28
Cache read $/M
$0.0028
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 82% of the 7,784 models listed
Input price$0.14
Cheaper than 76% 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, minimal, low, medium, high, xhigh, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
| Cache read | $0.0028 |