DeepSeek
DeepSeek API pricing per million tokens for DeepSeek V4.1 Flash and V4 Pro, at peak rates.
| Name | Provider | Input, $ per 1M tokens | Output, $ per 1M tokens | Sample request (10K in, 2K out), $ | Context window, tokens | Status |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | $0.0054 | 1M | Current |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $3.96 | $0.0211 | 1M | Current |
Prices come from DeepSeek’s pricing page. DeepSeek charges half price outside its peak hours (01:00-04:00 and 06:00-10:00 UTC on weekdays); the table shows the peak rate.
Questions
When are DeepSeek’s peak hours? 01:00-04:00 and 06:00-10:00 UTC on weekdays. Outside those hours DeepSeek charges half price.
Which rate does the table show? The peak rate, which is the higher one.
Which DeepSeek model costs less? DeepSeek V4.1 Flash: a request with 10,000 input and 2,000 output tokens costs about $0.0054 at peak, against about $0.021 for DeepSeek V4 Pro.
Sources
Prices are read from each provider’s official pricing page: OpenAI, Anthropic, Google Gemini API, xAI, DeepSeek and Mistral AI. Context and output limits that a provider does not publish come from OpenRouter’s model listing. Each model’s Sources field lists the pages used and the date each was checked. How we check prices · Price change log