LLM Gateway
DeepSeek V4 Flash (DeepInfra)
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
deepinfra/deepseek-v4-flashContext
1M
Max output
393.2K
Input $/M
$0.08
Output $/M
$0.18
Cache read $/M
$0.016
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 82% of the 7,784 models listed
Input price$0.08
Cheaper than 84% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputnot supported
Attachmentsnot supported
Temperaturesupported
Open weightssupported
Interleaved thinkingsupported
Modalities
Input
Text
Output
Text
Reasoning controls
effortnone, low, high, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.08 |
| Output | $0.18 |
| Cache read | $0.016 |