Pricing

This page describes the pricing of the DeepSeek API models.

MODELdeepseek-v4-flashdeepseek-v4-prodeepseek-v4-flash-vision-exp
BASE URL (OpenAI Format)https://api.deepseek.com
MODEL VERSIONDeepSeek-V4-Flash-0731DeepSeek-V4-Pro-0813DeepSeek-V4-Flash-Vision-Exp
CONTEXT LENGTH1M
MAX OUTPUTMAXIMUM: 384K
PRICING(1)(2)1M INPUT TOKENS
(CACHE HIT)
OFF-PEAK$0.007$0.022$0.007
PEAK$0.014$0.044$0.014
1M INPUT TOKENS
(CACHE MISS)
OFF-PEAK$0.22$0.66$0.22
PEAK$0.44$1.32$0.44
1M OUTPUT TOKENSOFF-PEAK$0.66$1.98$0.66
PEAK$1.32$3.96$1.32
Concurrency Limit(3)25005002500

(1) Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC (all other hours are off-peak).

(2) Images sent to deepseek-v4-flash-vision-exp are converted into tokens based on their dimensions and billed as input tokens.

(3) Concurrency limits may vary by account tier.

(4) Weekend discounts in Beijing Time are being rolled out — details to follow.