Every host for Nemotron 3.5 Lightning
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| Darkbloom | $0.049 | $0.025 | $0.12 | $0.013 | int4 | 99.8% |
| Io Net | $0.069 | $0.047 | $0.134 | $0.023 | — | 99.2% |
| DeepInfra | $0.085 | $0.06 | $0.16 | $0.03 | bf16 | 100.0% |
| CoreWeave | $0.103 | $0.07 | $0.20 | $0.04 | bf16 | 100.0% |
| Nebius | $0.105 | $0.06 | $0.24 | — | — | — |
Cheapest price over time
- Input
- Output
What your workload costs
- Darkbloom$19.50
- Io Net$27.47
- DeepInfra$34.00
- CoreWeave$41.00
- Nebius$42.00
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 346B tokens/mo
- Needed around the clock
- 132K tok/s
8 × H100 cost $16,878 a month. The cheapest API (Darkbloom) charges $0.049 per 1M blended tokens, so the GPUs only pay off above 346B tokens a month: the box must serve 132K 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 NVIDIA
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.