GPU cloud · 4 GPU models tracked
RunComfy
$2.50–$9.59per GPU-hour, the cheapest row to the dearest
Hosted ComfyUI service that rents a private machine with one GPU by the second for image and video workflows. Its pricing page lists an hourly pay-as-you-go price per machine size; the figure here is that price in US dollars as printed, for the whole machine (the GPU with the vCPUs and memory shown beside it). Machine sizes that name two possible cards are not listed, and the lower Pro rates need a monthly subscription. The page says nothing about VAT.
As of , RunComfy lists 4 GPU models we track, from $2.50 per GPU-hour (NVIDIA RTX A6000, on-demand) to $9.59 (NVIDIA H200, on-demand).
| Website | www.runcomfy.com/ |
|---|---|
| Pricing page | www.runcomfy.com/pricing |
| Regions and tiers | No region or tier named in the rates below: one global rate card |
| Models tracked | 4 |
Price by GPU
As of , per GPU-hour: RunComfy’s on-demand rate for each card it lists, a cheaper market it also sells, and where the on-demand rate stands among the providers we track.
| GPU | RunComfy on-demand, per GPU-hour | Against the market (median rate card) |
|---|---|---|
| NVIDIA H200 | $9.59 captured Deploy ↗ | 110% above the median $4.56 · 56 providers 53 of 56 list lower · lowest Dataoorts $2.29 |
| NVIDIA H100 80GB (form factor not stated) | $7.49 captured Deploy ↗ | 100% above the median $3.75 · 28 providers 25 of 28 list lower · lowest Gcore $1.72 · compare |
| NVIDIA A100 80GB | $4.99 captured Deploy ↗ | 151% above the median $1.99 · 63 providers 58 of 63 list lower · lowest Yotta Labs $0.92 · compare |
| NVIDIA RTX A6000 | $2.50 captured Deploy ↗ | 324% above the median $0.59 · 21 providers 20 of 21 list lower · lowest Thunder Compute $0.35 · compare |
The same, in words
- RunComfy lists the NVIDIA H200 from $9.59 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Oct 11, 2026 (7-day change: none). Against the market: 110% above the median rate card ($4.56 across 56 providers); 53 of the 56 providers we track list a lower on-demand rate, the lowest Dataoorts at $2.29 (Dataoorts’s rates).
- RunComfy lists the NVIDIA H100 80GB (form factor not stated) from $7.49 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Oct 11, 2026 (7-day change: none). Against the market: 100% above the median rate card ($3.75 across 28 providers); 25 of the 28 providers we track list a lower on-demand rate, the lowest Gcore at $1.72 (Gcore’s rates, RunComfy vs Gcore).
- RunComfy lists the NVIDIA A100 80GB from $4.99 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Oct 11, 2026 (7-day change: none). Against the market: 151% above the median rate card ($1.99 across 63 providers); 58 of the 63 providers we track list a lower on-demand rate, the lowest Yotta Labs at $0.92 (Yotta Labs’s rates, RunComfy vs Yotta Labs).
- RunComfy lists the NVIDIA RTX A6000 from $2.50 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Oct 11, 2026 (7-day change: none). Against the market: 324% above the median rate card ($0.59 across 21 providers); 20 of the 21 providers we track list a lower on-demand rate, the lowest Thunder Compute at $0.35 (Thunder Compute’s rates, RunComfy vs Thunder Compute).
All listed prices
One table per price type, never mixed. Every rate normalized to one GPU for one hour; a price opens the page it was read from, and 7d marks a rate that moved in the past seven days. The day each figure was first listed is in this page’s data, below.
On-demand
| GPU · what is sold | $ / GPU-hour | Read | Source |
|---|---|---|---|
| NVIDIA RTX A6000 | $2.50 | captured | Deploy ↗ |
| NVIDIA A100 80GB | $4.99 | captured | Deploy ↗ |
| NVIDIA H100 80GB (form factor not stated) | $7.49 | captured | Deploy ↗ |
| NVIDIA H200 | $9.59 | captured | Deploy ↗ |
Ask an AI agent about RunComfy’s rates: Claude, Cursor, VS Code and ChatGPT can read them through the GPU Economy MCP server - free, no key, every answer citing the page and read time.
Every rate on this page as data: /providers/runcomfy/prices.json — the same fields as prices.json, narrowed to this provider. CC BY 4.0, no key, no rate limit. On your own page: embed this table (/embed/providers/runcomfy, an iframe, no script).
Compare RunComfy with
Every provider that lists at least two of the same GPUs on-demand, most shared GPUs first; each opens the side-by-side page.
- EmpirioLabs 4 shared GPUs
- Koyeb 4 shared GPUs
- Sesterce 4 shared GPUs
- Yotta Labs 4 shared GPUs
- Barrack AI 3 shared GPUs
- Beam 3 shared GPUs
- Cerebrium 3 shared GPUs
- Deep Infra 3 shared GPUs
- E2E Networks 3 shared GPUs
- Gcore 3 shared GPUs
- GPU.ai 3 shared GPUs
- HexGrid 3 shared GPUs
- Hikube 3 shared GPUs
- Hugging Face 3 shared GPUs
- Hyperstack 3 shared GPUs
- immers.cloud 3 shared GPUs
- Lightning AI 3 shared GPUs
- Lium 3 shared GPUs
- Lyceum 3 shared GPUs
- Massed Compute 3 shared GPUs
- Northflank 3 shared GPUs
- Paperspace 3 shared GPUs
- RunPod 3 shared GPUs
- Seeweb 3 shared GPUs
- Vast.ai 3 shared GPUs
- Verda 3 shared GPUs
- Airon 2 shared GPUs
- Amazon Web Services 2 shared GPUs
- Bamboozle Web Services 2 shared GPUs
- Baseten 2 shared GPUs
- Civo 2 shared GPUs
- Cloud.ru Evolution 2 shared GPUs
- CloudGPU 2 shared GPUs
- CoreWeave 2 shared GPUs
- Crusoe 2 shared GPUs
- Daytona 2 shared GPUs
- fal 2 shared GPUs
- Fireworks AI 2 shared GPUs
- FlexAI 2 shared GPUs
- Geodd 2 shared GPUs
- GMI Cloud 2 shared GPUs
- Google Cloud 2 shared GPUs
- Jarvislabs 2 shared GPUs
- Krutrim Cloud 2 shared GPUs
- Lambda 2 shared GPUs
- Leafcloud 2 shared GPUs
- Microsoft Azure 2 shared GPUs
- Modal 2 shared GPUs
- Nebula Block 2 shared GPUs
- Oracle Cloud (OCI) 2 shared GPUs
- OVHcloud 2 shared GPUs
- Phala Cloud 2 shared GPUs
- QuantaCloud 2 shared GPUs
- Replicate 2 shared GPUs
- Runware 2 shared GPUs
- Servercore 2 shared GPUs
- SynpixCloud 2 shared GPUs
- Thunder Compute 2 shared GPUs
Data updated: