Vercel AI GatewayDeepSeek V4 Flash

Vercel AI Gateway

DeepSeek V4 Flash

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

deepseek/deepseek-v4-flash
Context
1M
Max output
384K
Input $/M
$0.13
Output $/M
$0.26
Cache read $/M
$0.028
Cache write $/M

Against the catalogue

Context window1M

Larger than 82% of the 7,784 models listed

Input price$0.13

Cheaper than 78% of priced models

Capabilities

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

Modalities

Input
Text
Output
Text

Reasoning controls

toggle
efforthigh, xhigh

Pricing detail

RateBase $/M
Input$0.13
Output$0.26
Cache read$0.028