GMI CloudDeepSeek V4 Flash

GMI Cloud

DeepSeek V4 Flash

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

deepseek-ai/DeepSeek-V4-Flash
Context
1M
Max output
384K
Input $/M
$0.11
Output $/M
$0.22
Cache read $/M
$0.022
Cache write $/M

Against the catalogue

Context window1M

Larger than 84% of the 7,784 models listed

Input price$0.11

Cheaper than 79% of priced models

Capabilities

Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentsnot supported
Temperaturesupported
Open weightssupported
Interleaved thinkingsupported

Modalities

Input
Text
Output
Text

Pricing detail

RateBase $/M
Input$0.11
Output$0.22
Cache read$0.022