DeepSeek V4 Pro
DeepSeek V4 Pro API pricing is $1.32 per million input tokens and $3.96 per million output tokens at peak.
- Provider
- DeepSeek
- API model name
- deepseek-v4-pro
- Status
- Current
- Input, $ per 1M tokens
- $1.32
- Cached input, $ per 1M tokens
- $0.044
- Output, $ per 1M tokens
- $3.96
- Sample request (10K in, 2K out), $
- $0.0211
- Context window, tokens
- 1M
- Price checked on
- Official pricing page
- api-docs.deepseek.com
On DeepSeek’s own API, off-peak rates are half the peak price: $0.66 input and $1.98 output. A cache hit costs $0.044 per million tokens at peak. A request with 10,000 input tokens and 2,000 output tokens costs about $0.021 at peak rates, roughly four times DeepSeek V4.1 Flash. The model name deepseek-v4-pro currently serves DeepSeek-V4-Pro-0813. It accepts text only; the context window is 1M tokens and maximum output is 384K.
- Max output, tokens
- 384K
- Input types
- Text
- Open weights
- Yes
- Pricing notes
- Prices shown are DeepSeek's peak rates. Off-peak rates are half: peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, excluding Chinese public holidays. The model version behind this name is DeepSeek-V4-Pro-0813.
- Sources
Page URL Checked DeepSeek models and pricing https://api-docs.deepseek.com/quick_start/pricing 2026-10-21
Questions
How much does the DeepSeek V4 Pro API cost?
What is the API model name for DeepSeek V4 Pro?
deepseek-v4-pro in API calls to DeepSeek. The context window is 1M tokens, and a response can run to 384,000 output tokens.What does one DeepSeek V4 Pro request cost?
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