DeepSeek API pricing
Every DeepSeek model we track, with input, cached input and output cost in USD per 1M tokens. DeepSeek is among the cheapest capable APIs, with aggressive cache-hit pricing that rewards repeated prompt prefixes.
17 models · updated 2026-11-10 · prices in USD per 1,000,000 tokens
17
Models tracked
$0.006
Cheapest input — DeepSeek V4.1 Flash 1017
$0.955
Priciest input — DeepSeek V4 Pro 0423
1M
Largest context — DeepSeek V4.1 Flash 1017
Listed in the order DeepSeek publishes them.
| DeepSeek V4.1 Flash 1017Provider API | $0.006 | $0.005 | $0.500 | 1M |
|---|---|---|---|---|
| DeepSeek Pro LatestProvider API | $0.100 | $0.100 | $8.00 | 1M |
| DeepSeek Flash LatestProvider API | $0.006 | $0.005 | $0.500 | 1M |
| DeepSeek V4.1 FlashProvider API | $0.051 | $0.018 | $0.567 | 1M |
| DeepSeek V4 Flash Vision ExpProvider API | $0.440 | $0.014 | $1.32 | 1M |
| DeepSeek V4 Pro 0813Provider API | $0.111 | $0.097 | $4.44 | 1M |
| DeepSeek V4 Flash LatestProvider API | $0.043 | $0.035 | $0.300 | 1M |
| DeepSeek V4 Flash 0731Provider API | $0.043 | $0.035 | $0.300 | 1M |
| DeepSeek V4 Pro 0423Provider API | $0.955 | $0.080 | $1.91 | 1M |
| DeepSeek V4 Flash 0423Provider API | $0.091 | $0.018 | $0.182 | 1M |
| DeepSeek V3.2Provider API | $0.260 | $0.130 | $0.380 | 164K |
| DeepSeek V3.2 ExpProvider API | $0.270 | — | $0.410 | 164K |
| DeepSeek V3.1 TerminusProvider API | $0.270 | — | $1.00 | 164K |
| DeepSeek V3.1Provider API | $0.250 | $0.130 | $0.950 | 164K |
| R1 0528Provider API | $0.500 | $0.350 | $2.15 | 164K |
| DeepSeek V3 0324Provider API | $0.290 | $0.110 | $1.14 | 164K |
| DeepSeek V3Provider API | $0.320 | — | $0.890 | 164K |
DeepSeek pricing questions
- How much does the DeepSeek API cost?
- DeepSeek pricing runs from $0.006 to $0.955 per 1M input tokens depending on the model. DeepSeek V4 Pro 0423 costs $0.955 per 1M input and $1.91 per 1M output tokens.
- What is the cheapest DeepSeek model?
- DeepSeek V4.1 Flash 1017 is the cheapest DeepSeek model we track, at $0.006 per 1M input tokens and $0.500 per 1M output tokens.
- Does DeepSeek charge less for cached tokens?
- Yes. Cached input is billed at a lower rate than fresh input — for DeepSeek V4.1 Flash 1017 it is $0.005 per 1M versus $0.006, about 17% cheaper. Caching applies to repeated prompt prefixes.
- How often is this DeepSeek pricing updated?
- Every day. Prices are read directly from the published pricing page, normalized to USD per 1,000,000 tokens, and only recorded when a number actually changes — so the history shows real price movements rather than daily noise.