Every host for Mistral Small 3.2 24B
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| DeepInfra | $0.106 | $0.075 | $0.20 | — | fp8 | 99.9% |
| Venice | $0.133 | $0.094 | $0.25 | — | fp8 | 99.7% |
| Parasail | $0.143 | $0.09 | $0.30 | $0.05 | bf16 | 100.0% |
| Mistral | $0.15 | $0.10 | $0.30 | $0.01 | — | 100.0% |
Cheapest price over time
- Input
- Output
What your workload costs
- DeepInfra$42.50
- Venice$53.13
- Parasail$57.00
- Mistral$60.00
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 159B tokens/mo
- Needed around the clock
- 60.4K tok/s
8 × H100 cost $16,878 a month. The cheapest API (DeepInfra) charges $0.106 per 1M blended tokens, so the GPUs only pay off above 159B tokens a month: the box must serve 60.4K 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.