DeepSeek API pricing, checked at the source
Peak and off-peak prices for deepseek-flash and deepseek-v4-pro, read off DeepSeek's own pricing page with a link on every row. Estimate a monthly bill below.
DeepSeek API prices per 1M tokens
Standard prices in USD. Each row links to DeepSeek's pricing page and shows the day we checked it.
| Model | Input | Cached input | Output | Notes | Source |
|---|---|---|---|---|---|
| deepseek-flashpeak hours | $0.30 | $0.006 | $1.20 | Served by DeepSeek-V4.1-Flash-1017. Off-peak: $0.15 input, $0.003 cache hit, $0.60 output. | Sourcechecked 2026-10-25 |
| deepseek-v4-propeak hours | $1.32 | $0.044 | $3.96 | DeepSeek-V4-Pro-0813. Off-peak: $0.66 input, $0.022 cache hit, $1.98 output. | Sourcechecked 2026-10-25 |
Terms on this page: Token · Prompt caching · Context window · Batch API
Estimate your DeepSeek bill
Enter your monthly tokens and how they split between new input, cached input and output. The result updates as you type.
Write 40k, 250M or 5B. Input, cached input and output tokens together.
100M tokens a month costs from $17.45 (deepseek-flash) to $71.19 (deepseek-v4-pro).
| Model | Per month | Per 1M tokens at this split |
|---|---|---|
| deepseek-flashpeak hours | $17.45 | $0.17448 |
| deepseek-v4-propeak hours | $71.19 | $0.71192 |
Standard prices in USD on 2026-10-25, before tax. Long-prompt tiers are left out; see the price table.
How the bill is worked out
Peak and off-peak
Cache hits
Context and output
Search and Fetch
DeepSeek API pricing questions
How much does the DeepSeek API cost?
DeepSeek bills its language models per million tokens, with separate prices for input, cached input and output. On 2026-10-25, standard prices ran from $0.30 (deepseek-flash) to $1.32 (deepseek-v4-pro) per 1M input tokens, and $1.20 (deepseek-flash) to $3.96 (deepseek-v4-pro) per 1M output tokens.
Does DeepSeek offer a batch discount?
Its pricing page lists no batch price for the rows here. Off-peak rates are half the peak rates. Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, excluding Chinese public holidays. Weekends and those holidays are off-peak all day.
How does prompt caching change a DeepSeek bill?
Input tokens that hit the cache are billed at the cache-hit price, a small fraction of the cache-miss price. There is no separate cache-write charge.
Where do these prices come from?
From DeepSeek's own pricing page, https://api-docs.deepseek.com/quick_start/pricing, checked on 2026-10-25. Every row links to it. When a price cannot be confirmed, the row says to check the vendor's page instead of showing a number.
When are DeepSeek's off-peak hours?
Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, excluding Chinese public holidays. Every other hour is off-peak, including weekends, and off-peak rates are half the peak rates. Work that can wait costs half as much if it runs off-peak.
Compare and plan
Building with the DeepSeek API? OceanLab builds AI into business workflows, with people kept in charge. AI automation →
