DeepSeek API pricing
ModelInput / 1MCached / 1MOutput / 1MPer monthAA Intelligence Index
DeepSeek V4.1 Flash$0.300$0.0060$1.20$3639.5
DeepSeek V4 Flash$0.440$0.014$1.32$46.234.3
DeepSeek V4 Pro$1.32$0.044$3.96$13936.0

Per month: 1,000 requests a day, 2,000 input and 500 output tokens each, no caching, 30 days.

Data: real-api-pricing (MIT) · prices as of Oct 16, 2026

Questions

What is the cheapest DeepSeek API model?
DeepSeek V4.1 Flash has the lowest list price of the 3 DeepSeek models here: $0.300 per 1M input tokens and $1.20 per 1M output tokens. At 1,000 requests a day (2,000 input and 500 output tokens each) that comes to about $36 a month.
Which DeepSeek model costs the most?
DeepSeek V4 Pro, at $1.32 per 1M input tokens and $3.96 per 1M output tokens: about $139 a month for the same workload.
Is cached input cheaper on DeepSeek?
Yes. On DeepSeek V4.1 Flash, cached input is $0.0060 per 1M tokens against $0.300 for fresh input.