GPU cloud · 5 GPU models tracked
Deep Infra
$0.89–$4.89per 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 $0.89 per GPU-hour (NVIDIA A100 80GB, on-demand) to $4.89 (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, cheapest tier first named:
- Deep Infra lists the NVIDIA B300 from $4.89 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 27, 2026. Against the market: the lowest on-demand rate of the 18 providers we track for this card, 38% below the median rate card ($7.94 across 18 providers).
- Deep Infra lists the NVIDIA B200 from $3.69 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 27, 2026. Against the market: the lowest on-demand rate of the 27 providers we track for this card, 46% below the median rate card ($6.79 across 27 providers).
- Deep Infra lists the NVIDIA H200 from $2.69 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 27, 2026. Against the market: 39% below the median rate card ($4.38 across 38 providers); 3 of the 38 providers we track list a lower on-demand rate, the lowest Beam at $2.09 (Beam’s rates, Deep Infra vs Beam).
- Deep Infra lists the NVIDIA H100 80GB (form factor not stated) from $2.20 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 27, 2026. Against the market: 21% below the median rate card ($2.79 across 19 providers); 3 of the 19 providers we track list a lower on-demand rate, the lowest Gcore at $1.74 (Gcore’s rates, Deep Infra vs Gcore).
- Deep Infra lists the NVIDIA A100 80GB from $0.89 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 27, 2026. Against the market: the lowest on-demand rate of the 40 providers we track for this card, 51% below the median rate card ($1.81 across 40 providers).
All listed prices
One table per price type, never mixed. Every rate normalized to one GPU for one hour.
On-demand
| GPU | USD / GPU-hour | 7-day change | Type | Region | Min. commitment | Source, captured | Deploy |
|---|---|---|---|---|---|---|---|
| NVIDIA A100 80GB | $0.89 | — | on-demand | — | — | Price page unchanged since first read, Sep 27, 2026 | Deploy ↗ |
| NVIDIA H100 80GB (form factor not stated) | $2.20 | — | on-demand | — | — | Price page unchanged since first read, Sep 27, 2026 | Deploy ↗ |
| NVIDIA H200 | $2.69 | — | on-demand | — | — | Price page unchanged since first read, Sep 27, 2026 | Deploy ↗ |
| NVIDIA B200 | $3.69 | — | on-demand | — | — | Price page unchanged since first read, Sep 27, 2026 | Deploy ↗ |
| NVIDIA B300 | $4.89 | — | on-demand | — | — | Price page unchanged since first read, Sep 27, 2026 | Deploy ↗ |
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.
- EmpirioLabs 5 shared GPUs
- Lyceum 5 shared GPUs
- Amazon Web Services 4 shared GPUs
- Cerebrium 4 shared GPUs
- Daytona 4 shared GPUs
- E2E Networks 4 shared GPUs
- fal 4 shared GPUs
- Gcore 4 shared GPUs
- Hugging Face Inference Endpoints 4 shared GPUs
- Hyperstack 4 shared GPUs
- Koyeb 4 shared GPUs
- Modal 4 shared GPUs
- Oracle Cloud (OCI) 4 shared GPUs
- RunPod 4 shared GPUs
- Sesterce 4 shared GPUs
- Verda 4 shared GPUs
- Baseten 3 shared GPUs
- Beam 3 shared GPUs
- CoreWeave 3 shared GPUs
- GMI Cloud 3 shared GPUs
- Google Cloud 3 shared GPUs
- HexGrid 3 shared GPUs
- immers.cloud 3 shared GPUs
- Nebius 3 shared GPUs
- Paperspace 3 shared GPUs
- Together AI 3 shared GPUs
- Vast.ai 3 shared GPUs
- Civo 2 shared GPUs
- Cloud.ru Evolution 2 shared GPUs
- Crusoe 2 shared GPUs
- Hyperbolic 2 shared GPUs
- Jarvislabs 2 shared GPUs
- Lambda 2 shared GPUs
- Leafcloud 2 shared GPUs
- Massed Compute 2 shared GPUs
- Microsoft Azure 2 shared GPUs
- Northflank 2 shared GPUs
- OVHcloud 2 shared GPUs
- packet.ai 2 shared GPUs
- Replicate 2 shared GPUs
- Seeweb 2 shared GPUs
Data updated: