OpenCode Go
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
$0.15
Output $/M
$0.60
Cache read $/M
$0.003
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 82% of the 7,784 models listed
Input price$0.15
Cheaper than 73% 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 | $0.15 |
| Output | $0.60 |
| Cache read | $0.003 |