DeepSeek API pricing 2026
DeepSeek API pricing covers two current models. DeepSeek V4.1 Flash costs $0.30 per million input tokens and $1.20 per million output tokens at peak times, and V4 Pro costs $1.32 and $3.96. Off-peak rates are half price, and cache hits cost far less: $0.006 and $0.044 per million at peak. Both models have a 1M token context and up to 384K output tokens.
DeepSeek prices per 1M tokens
| Model | Input | Cached | Output | Context |
|---|---|---|---|---|
DeepSeek V4.1 Flashdeepseek-flashPeak price. Off-peak: $0.15 in, $0.60 out. Max output 384K tokens. | $0.30 | $0.006 | $1.20 | 1M |
DeepSeek V4 Prodeepseek-v4-proPeak price. Off-peak: $0.66 in, $1.98 out. Max output 384K tokens. | $1.32 | $0.044 | $3.96 | 1M |
Standard tier, US dollars. Source: DeepSeek API pricing, checked November 1, 2026.
DeepSeek cost calculator
Includes reasoning or thinking tokens.
Cache write fees are not included.
Estimate tokens from text
About 0 tokens
A rough count at about 4 characters per token for English. Every provider tokenizes differently; Anthropic says Claude 4.7 and later produce about 30% more tokens for the same text.
| Model | Per request | Per month |
|---|---|---|
| DeepSeek V4.1 Flash$0.30 in / $1.20 out | $0.003 | $30.00 |
| DeepSeek V4 Pro$1.32 in / $3.96 out | $0.013 | $125.40 |
Standard tier prices per 1M tokens. Batch processing is about half price at OpenAI, Anthropic and Google. Taxes, tool fees and free tiers are not included.
Caching, batch and other pricing rules
- Off-peak rates are half of peak. Peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday, excluding Chinese public holidays; all other hours, including weekends, are off-peak. Our table and calculator use peak prices, so estimates err high.
- Input is priced as a cache hit or a cache miss. The cached input column shows the cache hit price.
- Both models support thinking mode (the default) and non-thinking mode. FIM completion, in beta, works in non-thinking mode only.
- The legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp are still accepted; those requests are served by V4.1 Flash and billed at the Flash price.
- Server-side Search and Fetch tools cost $0.75 per 1,000 successful requests each, billed per request from 1 November 2026.
- The concurrency limit is 2,500 for V4.1 Flash and 500 for V4 Pro. Only V4.1 Flash supports vision.
Price change log
- First check. Per-request billing for the Search and Fetch tools starts on 1 November 2026, Beijing time.
FAQ
Is the DeepSeek API free?
There is no free tier on the pricing page. DeepSeek says charges come from a granted balance first, then your topped-up balance, but it does not state how much is granted.
When is the DeepSeek API cheaper?
Off-peak, when every rate is half price. Peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays, excluding Chinese public holidays. Weekends are off-peak all day.
What is the cheapest DeepSeek model?
DeepSeek V4.1 Flash (deepseek-flash): $0.30 per million input tokens and $1.20 per million output tokens at peak, or $0.15 and $0.60 off-peak. Cache hits cost $0.006 per million at peak.