1
Recorded offers · not live
1
Source-backed comparable prices · not live
1
GPU model labels
Unknown
Maximum recorded VRAM · scope varies
USD quotes; availability is not live. Storage, network and tax may cost extra.
| Model | Configuration / billing | Recorded hourly price | GPU count | Recorded VRAM | Availability | Provenance |
|---|---|---|---|---|---|---|
| H100 | NVIDIA HGX H100; On-demand | Recorded $4.5/GPU-hour USD | GPU count unknown | VRAM unknown | Availability unknown |
Verified 2026-11-01 Source reviewed 2026-11-01 nebius.com ↗EvidencePrice verified against source at 2026-11-01T17:18:58.460416+00:00; not live inventory. Public source reviewed 2026-11-01T17:14:59.434858+00:00 (not verification of this offer). Explicit agent review by OMP agent; official Nebius browser pricing table reviewed; manual_browser_import capture bd90f39838874ccf8f2066e374aaf555fa43383aa71b33b40de9e3884e96ca8e; review 56eee3ffd25f5fdfaba1ba8531723e5df8a81f5bf60a5b4fd620622e1a966889. Advertised source evidence, not live inventory; reviewer attested configuration and units. |
Public catalog explicitly offers GPU instances with vCPU/RAM specifications, on-demand consumption, and preemptible VM pricing.
GPU infrastructure is distinct from managed model APIs.
Service-source review confirms only the listed verified fields. It does not verify any price, region, GPU configuration, capacity or availability. Pricing-page links are not recorded price offers.
Confirm support for the exact accelerator and software version.
NVIDIA CUDA documentation ↗AMD ROCm compatibility documentation ↗Intel oneAPI documentation ↗