LLM Gateway
DeepSeek V4 Flash (Consensus Protocol)
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
consensusprotocol/deepseek-v4-flashContext
1.1M
Max output
393.2K
Input $/M
$0.05
Output $/M
$0.10
Cache read $/M
$0.01
Cache write $/M
—
Against the catalogue
Context window1.1M
Larger than 99% of the 7,784 models listed
Input price$0.05
Cheaper than 87% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentsnot supported
Temperaturesupported
Open weightssupported
Interleaved thinkingsupported
Modalities
Input
Text
Output
Text
Reasoning controls
effortnone, low, high, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.05 |
| Output | $0.10 |
| Cache read | $0.01 |