Every host for DeepSeek V4 Flash Vision Exp
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| DeepInfra | $0.323 | $0.216 | $0.647 | $0.0069 | fp8 | 100.0% |
| Fireworks | $0.33 | $0.22 | $0.66 | $0.007 | — | — |
| DeepSeek | $0.525 | $0.30 | $1.20 | $0.006 | — | — |
| GMI Cloud | $0.66 | $0.44 | $1.32 | $0.014 | fp8 | 99.9% |
| Novita | $0.66 | $0.44 | $1.32 | $0.028 | — | — |
| SiliconFlow | $0.66 | $0.44 | $1.32 | $0.028 | fp8 | 100.0% |
Cheapest price over time
- Input
- Output
What your workload costs
- DeepInfra$129.36
- Fireworks$132.00
- DeepSeek$210.00
- GMI Cloud$264.00
- Novita$264.00
- SiliconFlow$264.00
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 52.2B tokens/mo
- Needed around the clock
- 19.9K tok/s
8 × H100 cost $16,878 a month. The cheapest API (DeepInfra) charges $0.323 per 1M blended tokens, so the GPUs only pay off above 52.2B tokens a month: the box must serve 19.9K 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.