GPU Inference Leaderboard
Prices are collected automatically from providers' public pages and can be outdated or wrong. Confirm with the provider before you buy.
14 on-demand instances · Lowest price ($/GPU-hr, cheapest first) · as of 10 Nov 2026H200 · 141 GB
| Provider | GPU | Pricing page | ||||
|---|---|---|---|---|---|---|
| Crusoe | H200 · SXM | 141 GB | 1979 | BEST$2.30 | 100 | Pricing ↗ |
| Koyeb | H200 | 141 GB | 1979 | $3.00 | 77 | Pricing ↗ |
| Massed Compute | H200 · NVLink | 141 GB | 1979 | $3.62 | 64 | Pricing ↗ |
| Theta EdgeCloud | H200 | 141 GB | 1979 | $3.69 | 62 | Pricing ↗ |
| Hyperstack | H200 · SXM | 141 GB | 1979 | $3.99 | 58 | Pricing ↗ |
| DigitalOcean (Paperspace) | H200 · SXM | 141 GB | 1979 | $4.47 | 51 | Pricing ↗ |
| Daytona | H200 | 141 GB | 1979 | $4.54 | 51 | Pricing ↗ |
| Jarvis Labs | H200 · SXM | 141 GB | 1979 | $4.59 | 50 | Pricing ↗ |
| Runpod | H200 | 141 GB | 1979 | $5.29 | 43 | Pricing ↗ |
| Nebius | H200 · SXM | 141 GB | 1979 | $5.40 | 43 | Pricing ↗ |
| Spheron | H200 · SXM | 141 GB | 1979 | $5.52 | 42 | Pricing ↗ |
| Together AI | H200 · SXM | 141 GB | 1979 | $5.99 | 38 | Pricing ↗ |
| CoreWeave | H200 · SXM | 141 GB | 1979 | $6.30 | 36 | Pricing ↗ |
| Verda (formerly DataCrunch) | H200 · SXM | 141 GB | 1979 | $6.44 | 36 | Pricing ↗ |
- $2.30per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPSBESTPricing ↗
- $3.00per GPU-hrH200 · 141 GB · 1979 TFLOPS
- $3.62per GPU-hrH200 · NVLink · 141 GB · 1979 TFLOPS
- $3.69per GPU-hrH200 · 141 GB · 1979 TFLOPS
- $3.99per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $4.47per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $4.54per GPU-hrH200 · 141 GB · 1979 TFLOPS
- $4.59per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $5.29per GPU-hrH200 · 141 GB · 1979 TFLOPS
- $5.40per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $5.52per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $5.99per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $6.30per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
- $6.44per GPU-hrH200 · SXM · 141 GB · 1979 TFLOPS
1–14 of 14