GPU cloud · 5 GPU models tracked
Deep Infra
$1.49–$5.89per GPU-hour, the cheapest row to the dearest
Dedicated GPUs for a model you deploy on Deep Infra, billed by the minute for the time they are up and shown here as an hour; the page prices no CPU or memory apart from them. Its per-token model pricing is a different product and is not listed here.
As of , Deep Infra lists 5 GPU models we track, from $1.49 per GPU-hour (NVIDIA A100 80GB, on-demand) to $5.89 (NVIDIA B300, on-demand).
| Website | deepinfra.com/ |
|---|---|
| Pricing page | deepinfra.com/pricing |
| Regions and tiers | No region or tier named in the rates below: one global rate card |
| Models tracked | 5 |
Price by GPU
As of , per GPU-hour: Deep Infra’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 | Deep Infra on-demand, per GPU-hour | Against the market (median rate card) |
|---|---|---|
| NVIDIA B300 | $5.89 captured Deploy ↗ | 35% below the median $9.00 · 26 providers the lowest on-demand rate of the 26 |
| NVIDIA B200 | $4.89 captured Deploy ↗ | 32% below the median $7.17 · 37 providers 1 of 37 list lower · lowest Hostinger $4.50 from · compare |
| NVIDIA H200 | $3.49 captured Deploy ↗ | 23% below the median $4.54 · 53 providers 9 of 53 list lower · lowest Dataoorts $2.29 · compare |
| NVIDIA H100 80GB (form factor not stated) | $2.90 captured Deploy ↗ | 17% below the median $3.50 · 25 providers 5 of 25 list lower · lowest Koyeb $2.50 · compare |
| NVIDIA A100 80GB | $1.49 captured Deploy ↗ | 27% below the median $2.04 · 60 providers 12 of 60 list lower · lowest Yotta Labs $0.92 · compare |
The same, in words
- Deep Infra lists the NVIDIA B300 from $5.89 per GPU-hour on-demand. The on-demand rate is unchanged since Oct 20, 2026 (7-day change: none). Against the market: the lowest on-demand rate of the 26 providers we track for this card, 35% below the median rate card ($9.00 across 26 providers).
- Deep Infra lists the NVIDIA B200 from $4.89 per GPU-hour on-demand. The on-demand rate is unchanged since Oct 20, 2026 (7-day change: none). Against the market: 32% below the median rate card ($7.17 across 37 providers); 1 of the 37 providers we track list a lower on-demand rate, the lowest Hostinger at $4.50 (Hostinger’s rates, Deep Infra vs Hostinger).
- Deep Infra lists the NVIDIA H200 from $3.49 per GPU-hour on-demand. The on-demand rate is unchanged since Oct 20, 2026 (7-day change: none). Against the market: 23% below the median rate card ($4.54 across 53 providers); 9 of the 53 providers we track list a lower on-demand rate, the lowest Dataoorts at $2.29 (Dataoorts’s rates, Deep Infra vs Dataoorts).
- Deep Infra lists the NVIDIA H100 80GB (form factor not stated) from $2.90 per GPU-hour on-demand. The on-demand rate is unchanged since Oct 20, 2026 (7-day change: none). Against the market: 17% below the median rate card ($3.50 across 25 providers); 5 of the 25 providers we track list a lower on-demand rate, the lowest Koyeb at $2.50 (Koyeb’s rates, Deep Infra vs Koyeb).
- Deep Infra lists the NVIDIA A100 80GB from $1.49 per GPU-hour on-demand. The on-demand rate is unchanged since Oct 20, 2026 (7-day change: none). Against the market: 27% below the median rate card ($2.04 across 60 providers); 12 of the 60 providers we track list a lower on-demand rate, the lowest Yotta Labs at $0.92 (Yotta Labs’s rates, Deep Infra vs Yotta Labs).
Dated pieces on Deep Infra: — Deep Infra raised five GPU rates October 20, 2026: H100 $2.20 to $2.90. Each is frozen as of its date.
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 A100 80GB | $1.49 | captured | Deploy ↗ |
| NVIDIA H100 80GB (form factor not stated) | $2.90 | captured | Deploy ↗ |
| NVIDIA H200 | $3.49 | captured | Deploy ↗ |
| NVIDIA B200 | $4.89 | captured | Deploy ↗ |
| NVIDIA B300 | $5.89 | captured | Deploy ↗ |
Ask an AI agent about Deep Infra’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/deepinfra/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/deepinfra, an iframe, no script).
Compare Deep Infra 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.
- Lyceum 5 shared GPUs
- Runcrate 5 shared GPUs
- Yotta Labs 5 shared GPUs
- Amazon Web Services 4 shared GPUs
- Barrack AI 4 shared GPUs
- Cerebrium 4 shared GPUs
- Daytona 4 shared GPUs
- E2E Networks 4 shared GPUs
- EmpirioLabs 4 shared GPUs
- fal 4 shared GPUs
- Gcore 4 shared GPUs
- GPU.ai 4 shared GPUs
- Hugging Face 4 shared GPUs
- Hyperstack 4 shared GPUs
- Koyeb 4 shared GPUs
- Lium 4 shared GPUs
- Modal 4 shared GPUs
- Northflank 4 shared GPUs
- Oracle Cloud (OCI) 4 shared GPUs
- RunPod 4 shared GPUs
- Runware 4 shared GPUs
- Sesterce 4 shared GPUs
- Verda 4 shared GPUs
- Civo 3 shared GPUs
- CoreWeave 3 shared GPUs
- FarmGPU 3 shared GPUs
- FlexAI 3 shared GPUs
- GMI Cloud 3 shared GPUs
- Google Cloud 3 shared GPUs
- HexGrid 3 shared GPUs
- Hikube 3 shared GPUs
- immers.cloud 3 shared GPUs
- Nebius 3 shared GPUs
- OpenRelay 3 shared GPUs
- Paperspace 3 shared GPUs
- RunComfy 3 shared GPUs
- Together AI 3 shared GPUs
- Vast.ai 3 shared GPUs
- Bamboozle Web Services 2 shared GPUs
- Cloud.ru Evolution 2 shared GPUs
- Dataoorts 2 shared GPUs
- Elice Cloud 2 shared GPUs
- FPT AI Factory 2 shared GPUs
- Geodd 2 shared GPUs
- Hostinger 2 shared GPUs
- HPC-AI.COM 2 shared GPUs
- Hyperbolic 2 shared GPUs
- Jarvislabs 2 shared GPUs
- Leafcloud 2 shared GPUs
- Limestone Networks 2 shared GPUs
- Massed Compute 2 shared GPUs
- Microsoft Azure 2 shared GPUs
- OVHcloud 2 shared GPUs
- Phala Cloud 2 shared GPUs
- Replicate 2 shared GPUs
- Seeweb 2 shared GPUs
- Servercore 2 shared GPUs
Data updated: