DeepSeek API pricing
DeepSeek bills its API per 1M tokens. Two models are on the price table. deepseek-flash runs DeepSeek-V4.1-Flash-1017. deepseek-v4-pro runs DeepSeek-V4-Pro-0813. Rates change with the hour. Off-peak rates are half of peak rates. Figures come from the DeepSeek Models and Pricing page on October 27, 2026.
Rates per 1M tokens
| Item | deepseek-flash peak | deepseek-flash off-peak | deepseek-v4-pro peak | deepseek-v4-pro off-peak |
|---|---|---|---|---|
| Input, cache hit | $0.006 | $0.003 | $0.044 | $0.022 |
| Input, cache miss | $0.3 | $0.15 | $1.32 | $0.66 |
| Output | $1.2 | $0.6 | $3.96 | $1.98 |
Both models have a 1M context length. Max output is 384K. Concurrency limits are 2500 for Flash and 500 for V4 Pro.
Peak hours
Peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday through Friday. Chinese public holidays are off-peak. All other hours are off-peak, weekends included.
Search and Fetch APIs
| API | Price |
|---|---|
| Search | $0.75 per 1,000 successful requests |
| Fetch | $0.75 per 1,000 successful requests |
Server-side tool calls through DeepSeek Harness, Claude Code, or Codex hit these APIs. The page says those calls are free for now. Per-request billing starts at 00:00 Beijing time on November 1, 2026.
Billing rules
Cost is tokens times price. Fees come out of your topped-up balance or granted balance. The granted balance goes first. The legacy name deepseek-v4-flash works and bills at the Flash price.
Peak or off-peak for one job
Our math: a Flash job with 10M cache-miss input tokens and 1M output tokens costs $3 plus $1.2, or $4.20, at peak. The same job costs $1.50 plus $0.6, or $2.10, off-peak.
What we withhold
We do not convert UTC peak hours to other time zones. Holiday dates change each year, so check the DeepSeek page.
Compare and track
See the OpenAI API pricing guide, the Anthropic API pricing guide, the Together AI pricing guide, the OpenRouter pricing guide, and all AI tools.
FAQ
How much does the DeepSeek API cost? deepseek-flash costs $0.3 per 1M cache-miss input tokens and $1.2 per 1M output tokens at peak. deepseek-v4-pro costs $1.32 in and $3.96 out at peak.
Does DeepSeek have off-peak pricing? Yes. Off-peak rates are half of peak rates. Weekends are off-peak.
When are DeepSeek peak hours? 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday through Friday.
How much is a DeepSeek cache hit? $0.006 per 1M tokens on Flash at peak, and $0.044 on V4 Pro at peak.
What does the DeepSeek Search API cost? $0.75 per 1,000 successful requests. Fetch costs the same.
How we check
We rendered the DeepSeek Models and Pricing page on October 27, 2026. Get an alert when DeepSeek changes a price.
Checked 2026-10-27. Prices and policies change. Confirm on the source before you buy.
Sources
More guides
- 1Password pricing per user: Business plan cost (2026)
- ActiveCampaign pricing: plans, seats and contacts (2026)
- Ahrefs pricing per month: Lite, Standard, Advanced, and Enterprise (2026)
- Aircall pricing per user: Essentials, Professional, and the 3-license minimum (2026)
- Airtable pricing per user: who counts as a paid seat, and team totals (2026)
- Amazon Polly pricing: $4 to $100 per million characters (2026)