GPU cloud · 6 GPU models tracked
Baseten
$0.63–$9.98per GPU-hour, the cheapest row to the dearest
Dedicated model deployments billed by the minute and scaled down when idle, shown here as an hour; each price is a GPU instance with its CPU and memory.
As of , Baseten lists 6 GPU models we track, from $0.63 per GPU-hour (NVIDIA T4, on-demand) to $9.98 (NVIDIA B200, on-demand).
| Website | www.baseten.co/ |
|---|---|
| Pricing page | www.baseten.co/pricing/ |
| Regions and tiers | No region or tier named in the rates below: one global rate card |
| Models tracked | 6 |
Price by GPU
As of , per GPU-hour: Baseten’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 | Baseten on-demand, per GPU-hour | Against the market (median rate card) |
|---|---|---|
| NVIDIA B200 | $9.98 captured Deploy ↗ | 44% above the median $6.94 · 40 providers 34 of 40 list lower · lowest Hostinger $4.50 from · compare |
| NVIDIA H100 80GB (form factor not stated) | $6.50 captured Deploy ↗ | 73% above the median $3.75 · 28 providers 24 of 28 list lower · lowest Gcore $1.72 · compare |
| NVIDIA A100 80GB | $4.00 captured Deploy ↗ | 101% above the median $1.99 · 63 providers 56 of 63 list lower · lowest Yotta Labs $0.92 · compare |
| NVIDIA A10G | $1.21 captured Deploy ↗ | 7% above the median $1.13 · 4 providers 2 of 4 list lower · lowest Amazon Web Services $1.01 · compare |
| NVIDIA L4 | $0.85 captured Deploy ↗ | 6% above the median $0.80 · 23 providers 16 of 23 list lower · lowest Hikube $0.28 GPU only · compare |
| NVIDIA T4 | $0.63 captured Deploy ↗ | 15% above the median $0.55 · 19 providers 12 of 19 list lower · lowest immers.cloud $0.24 · compare |
The same, in words
- Baseten lists the NVIDIA B200 from $9.98 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 44% above the median rate card ($6.94 across 40 providers); 34 of the 40 providers we track list a lower on-demand rate, the lowest Hostinger at $4.50 (Hostinger’s rates, Baseten vs Hostinger).
- Baseten lists the NVIDIA H100 80GB (form factor not stated) from $6.50 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 73% above the median rate card ($3.75 across 28 providers); 24 of the 28 providers we track list a lower on-demand rate, the lowest Gcore at $1.72 (Gcore’s rates, Baseten vs Gcore).
- Baseten lists the NVIDIA A100 80GB from $4.00 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 101% above the median rate card ($1.99 across 63 providers); 56 of the 63 providers we track list a lower on-demand rate, the lowest Yotta Labs at $0.92 (Yotta Labs’s rates, Baseten vs Yotta Labs).
- Baseten lists the NVIDIA A10G from $1.21 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 27, 2026 (7-day change: none). Against the market: 7% above the median rate card ($1.13 across 4 providers); 2 of the 4 providers we track list a lower on-demand rate, the lowest Amazon Web Services at $1.01 (Amazon Web Services’s rates, Baseten vs Amazon Web Services).
- Baseten lists the NVIDIA L4 from $0.85 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 6% above the median rate card ($0.80 across 23 providers); 16 of the 23 providers we track list a lower on-demand rate, the lowest Hikube at $0.28 (Hikube’s rates, Baseten vs Hikube).
- Baseten lists the NVIDIA T4 from $0.63 per GPU-hour on-demand. The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 15% above the median rate card ($0.55 across 19 providers); 12 of the 19 providers we track list a lower on-demand rate, the lowest immers.cloud at $0.24 (immers.cloud’s rates, Baseten vs immers.cloud).
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 T4 | $0.63 | captured | Deploy ↗ |
| NVIDIA L4 | $0.85 | captured | Deploy ↗ |
| NVIDIA A10G | $1.21 | captured | Deploy ↗ |
| NVIDIA A100 80GB | $4.00 | captured | Deploy ↗ |
| NVIDIA H100 80GB (form factor not stated) | $6.50 | captured | Deploy ↗ |
| NVIDIA B200 | $9.98 | captured | Deploy ↗ |
Ask an AI agent about Baseten’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/baseten/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/baseten, an iframe, no script).
Compare Baseten 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.
- Amazon Web Services 5 shared GPUs
- Cerebrium 5 shared GPUs
- E2E Networks 5 shared GPUs
- EmpirioLabs 5 shared GPUs
- Hugging Face 5 shared GPUs
- Google Cloud 4 shared GPUs
- Koyeb 4 shared GPUs
- Lightning AI 4 shared GPUs
- Modal 4 shared GPUs
- Northflank 4 shared GPUs
- Sesterce 4 shared GPUs
- airgpu 3 shared GPUs
- Bamboozle Web Services 3 shared GPUs
- Deep Infra 3 shared GPUs
- GPU.ai 3 shared GPUs
- Hikube 3 shared GPUs
- immers.cloud 3 shared GPUs
- Lyceum 3 shared GPUs
- Replicate 3 shared GPUs
- RunPod 3 shared GPUs
- Vast.ai 3 shared GPUs
- Yotta Labs 3 shared GPUs
- Barrack AI 2 shared GPUs
- Beam 2 shared GPUs
- Cloud.ru Evolution 2 shared GPUs
- CoreWeave 2 shared GPUs
- Daytona 2 shared GPUs
- Elice Cloud 2 shared GPUs
- fal 2 shared GPUs
- Fireworks AI 2 shared GPUs
- FlexAI 2 shared GPUs
- Gcore 2 shared GPUs
- GMI Cloud 2 shared GPUs
- HexGrid 2 shared GPUs
- Hostinger 2 shared GPUs
- Hyperstack 2 shared GPUs
- Inferless 2 shared GPUs
- Infomaniak 2 shared GPUs
- Jarvislabs 2 shared GPUs
- Krutrim Cloud 2 shared GPUs
- Lambda 2 shared GPUs
- Leafcloud 2 shared GPUs
- Lium 2 shared GPUs
- Massed Compute 2 shared GPUs
- Microsoft Azure 2 shared GPUs
- OpenRelay 2 shared GPUs
- Oracle Cloud (OCI) 2 shared GPUs
- OVHcloud 2 shared GPUs
- packet.ai 2 shared GPUs
- RunComfy 2 shared GPUs
- Runware 2 shared GPUs
- Seeweb 2 shared GPUs
- Vagon 2 shared GPUs
- Verda 2 shared GPUs
- Yandex Cloud 2 shared GPUs
Data updated: