LLM Gateway
DeepSeek V4 Flash (Runware)
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
runware/deepseek-v4-flashContext
1M
Max output
384K
Input $/M
$0.076
Output $/M
$0.15
Cache read $/M
$0.014
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 95% of the 7,784 models listed
Input price$0.076
Cheaper than 85% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentsnot supported
Temperaturesupported
Open weightssupported
Interleaved thinkingsupported
Modalities
Input
Text
Output
Text
Reasoning controls
effortnone, high, xhigh, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.076 |
| Output | $0.15 |
| Cache read | $0.014 |