deepseek-v4-flash
DeepSeek/deepseek-v4-flash
llmDeepSeekdeepseek-v4-flash
No introduction yet. It will appear when the API includes intro, description, or capability text for this model.
deepseek-v4-flash — Groups & pricing
default
Save 40%Current: Off-peakPeak hours are 09:00-12:00 and 14:00-18:00 Beijing time, Monday through Friday.Any unconfigured peak rate uses its matching off-peak rate.
Off-peakCurrent
Input
$0.0857/ 1M tokens
Cache read
$0.0017/ 1M tokens
Output
$0.3429/ 1M tokens
Peak
Input
$0.1714/ 1M tokens
Cache read
$0.0034/ 1M tokens
Output
$0.6857/ 1M tokens
Example code & API
Documentation is being updated