Every host for Mistral Nemo
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| Io Net | $0.018 | $0.017 | $0.022 | $0.011 | fp16 | 100.0% |
| Dekallm | $0.021 | $0.018 | $0.03 | — | fp8 | 100.0% |
| DeepInfra | $0.029 | $0.029 | $0.03 | — | fp8 | 100.0% |
| Parasail | $0.03 | $0.03 | $0.03 | — | fp8 | 100.0% |
| Novita | $0.073 | $0.04 | $0.17 | — | — | — |
| Azure | $0.15 | $0.15 | $0.15 | — | — | — |
| Mistral | $0.15 | $0.15 | $0.15 | $0.015 | — | 100.0% |
Cheapest price over time
- Input
- Output
What your workload costs
- Io Net$7.13
- Dekallm$8.40
- DeepInfra$11.70
- Parasail$12.00
- Novita$29.00
- Azure$60.00
- Mistral$60.00
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 947B tokens/mo
- Needed around the clock
- 360K tok/s
8 × H100 cost $16,878 a month. The cheapest API (Io Net) charges $0.018 per 1M blended tokens, so the GPUs only pay off above 947B tokens a month: the box must serve 360K 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 Mistral
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.