DeepSeek API pricing
DeepSeek charges per million tokens, with a lower rate for the tokens you send than for the tokens the model writes. The 2 DeepSeek models we track run from $0.30 / $1.20 (DeepSeek V4.1 Flash) to $1.32 / $3.96 (DeepSeek V4 Pro).
Prices from DeepSeek’s official pricing page, verified October 3, 2026.
Every DeepSeek model, cheapest first
USD per 1M tokens, standard tier.
| Model | Input | Cached input | Output | Long context | Batch | Context |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash deepseek-flash | $0.30 | $0.006 | $1.20 | — | — | 1M tokens |
| DeepSeek V4 Pro deepseek-v4-pro | $1.32 | $0.044 | $3.96 | — | — | 1M tokens |
DeepSeek API cost calculator
- $156.00/mo$0.0031 / request
- DeepSeek V4 ProDeepSeek$646.80/mo$0.01 / request
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.
Pricing details by model
- DeepSeek V4.1 Flash
- Prices shown are peak rates. Off-peak rates are half: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday.
- Compatible with both OpenAI-format and Anthropic-format APIs.
- DeepSeek V4 Pro
- Prices shown are peak rates. Off-peak rates are half: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday.
- Vision input is not supported.
Frequently asked questions
- How much does the DeepSeek API cost?
- DeepSeek API prices range from $0.30 input / $1.20 output per 1M tokens for DeepSeek V4.1 Flash to $1.32 / $3.96 for DeepSeek V4 Pro. A support chatbot handling 100,000 replies a month costs about $93.00 on DeepSeek V4.1 Flash.
- What is the cheapest DeepSeek model?
- DeepSeek V4.1 Flash, at a blended $0.525 per 1M tokens (3 input : 1 output) — 73% less per token than DeepSeek V4 Pro.
- Which DeepSeek model is the most capable?
- DeepSeek V4 Pro has the highest Epoch Capabilities Index of the DeepSeek models we track (155.5), at $1.32 input / $3.96 output per 1M tokens.