Every host for DeepSeek V3
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| Inferenceapis | $0.238 | $0.19 | $0.38 | $0.04 | — | — |
| DeepSeek | $0.315 | $0.28 | $0.42 | $0.028 | — | — |
| DeepInfra | $0.37 | $0.256 | $0.712 | — | fp4 | 100.0% |
| Streamlake | $0.45 | $0.257 | $1.03 | — | — | 100.0% |
Cheapest price over time
- Input
- Output
What your workload costs
- Inferenceapis$95.00
- DeepSeek$126.00
- DeepInfra$148.00
- Streamlake$180.09
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 71.1B tokens/mo
- Needed around the clock
- 27K tok/s
8 × H100 cost $16,878 a month. The cheapest API (Inferenceapis) charges $0.238 per 1M blended tokens, so the GPUs only pay off above 71.1B tokens a month: the box must serve 27K tokens a second, every second.
GPU price: cheapest on-demand offer per GPU-hour × 730 hours. No throughput is assumed: it depends on the model size, precision, batch size and serving software, so measure yours. Power, storage, egress and engineering time are not included.
More from DeepSeek
Quality data: LMArena (CC BY 4.0), Epoch AI (CC BY 4.0). Prices: OpenRouter, LiteLLM (MIT), provider pages. List prices in US dollars before discounts and taxes; other currencies converted at the European Central Bank reference rate. The figures on these pages are free to reuse under CC BY 4.0 with a link to this page.