DeepSeek API pricing
Current DeepSeek rates and model costs for high-volume API workloads.
Compare one workload
Rates only become comparable when input, output and request count are identical. The calculation below uses the same workload for every model.
- Input per request
- 2,000
- Output per request
- 1,000
- Requests
- 1,000
Current model costs
| Model | Input / 1M | Output / 1M | Workload estimate |
|---|---|---|---|
| DeepSeek: DeepSeek V4.1 FlashDeepseek | $0.03 | $0.5 | $0.56 |
| DeepSeek: DeepSeek V4 Flash Vision ExpDeepseek | $0.22 | $0.65 | $1.08 |
| DeepSeek: DeepSeek V4 Pro 0813Deepseek | $0.66 | $1.98 | $3.3 |
| DeepSeek: DeepSeek V4 Flash 0731Deepseek | $0.01 | $1.28 | $1.3 |
| DeepSeek: DeepSeek V4 Pro 0423Deepseek | $0.21 | $0.42 | $0.84 |
| DeepSeek: DeepSeek V4 Flash 0423Deepseek | $0.04 | $0.08 | $0.17 |
| DeepSeek: DeepSeek V3.2Deepseek | $0.28 | $0.42 | $0.98 |
| DeepSeek: DeepSeek V3.2 ExpDeepseek | $0.27 | $0.41 | $0.95 |
| DeepSeek: DeepSeek V3.1 TerminusDeepseek | $0.3 | $1 | $1.6 |
| DeepSeek: DeepSeek V3.1Deepseek | $0.25 | $0.95 | $1.45 |
Estimate uses published token rates. Caching, reasoning tokens, tools, images, routing and taxes can change the final bill.
How much does the DeepSeek API cost?
Start with the work unit you can measure: one conversation, document, article or agent run. Record both prompt and response length, then multiply by real monthly volume. Output often costs more than input, so a concise answer can matter more than a short prompt.
Price is only one constraint. Check context length, modalities, tool support, latency and output quality before choosing a production model. Test a small representative sample instead of relying on a single benchmark.