GPU workload page

H100 NVL vLLM hosting price by provider

OpenAI-compatible vLLM serving usually starts at 24GB GPUs and moves into 80GB+ rows for larger models, batching, and long prompts. For H100 NVL, the current tracked provider floor is $2.27/hr on Vast.ai.

94GB HBM3 vLLM hosting 24GB+ floor Updated Jun 21, 2026
Cheapest provider
Vast.ai
$2.27/hr
Monthly estimate
$1,656/mo
730 hours at current median price
Provider coverage
3
3 current rows updated Jun 21, 2026
Market gap
+$1.87/hr
Floor is Vast.ai RTX 4090

Current H100 NVL rows for vLLM hosting

H100 NVL clears the 24GB+ filter for vLLM hosting. The broader vLLM hosting floor is $0.40/hr with RTX 4090 on Vast.ai, so the cheapest H100 NVL row is $1.87/hr above that floor.

Updated Jun 21, 2026
Provider Type Median hourly Monthly Workload page Offers Updated
Vast.ai on-demand $2.27/hr $1,656/mo Vast.ai vLLM hosting 9 Jun 21, 2026
RunPod on-demand $3.19/hr $2,329/mo RunPod vLLM hosting 1 Jun 21, 2026
Azure on-demand $6.98/hr $5,095/mo Azure vLLM hosting 6 Jun 21, 2026

H100 NVL for vLLM hosting: current provider pricing

This page starts with the GPU instead of the provider, then filters the live market to rows that match vLLM hosting. It is useful when you have already chosen H100 NVL and need the cheapest provider path for the workload.

Open-weight inference APIs, chat completions, and model serving teams comparing provider-specific GPU options. The table keeps provider/GPU and provider/workload links close together so you can keep narrowing the shortlist without going back to the homepage.

Cheapest provider right now

Cheapest H100 NVL provider for vLLM hosting

The cheapest tracked H100 NVL row for vLLM hosting is $2.27/hr on Vast.ai with on-demand pricing. The broader vLLM hosting floor is $0.40/hr with RTX 4090 on Vast.ai, so the cheapest H100 NVL row is $1.87/hr above that floor.

Methodology and freshness

How this GPU workload page is computed

We filter the compare payload to H100 NVL, require 24GB+ workload fit, and sort current on-demand provider rows by median hourly price.

H100 NVL vLLM hosting pricing FAQ

Is H100 NVL good for vLLM hosting?

H100 NVL clears the 24GB+ filter for vLLM hosting. The cheapest tracked H100 NVL row for vLLM hosting is $2.27/hr on Vast.ai with on-demand pricing.

What is the cheapest H100 NVL provider for vLLM hosting?

The cheapest tracked H100 NVL row for vLLM hosting is $2.27/hr on Vast.ai with on-demand pricing.

How does H100 NVL compare with the broader vLLM hosting market?

The broader vLLM hosting floor is $0.40/hr with RTX 4090 on Vast.ai, so the cheapest H100 NVL row is $1.87/hr above that floor.

How fresh is this H100 NVL vLLM hosting page?

The page is recalculated from the latest stored on-demand rows. The freshest qualifying row visible here is from Jun 21, 2026.