GPU cloud · 11 GPU models tracked
Modal
$0.59–$7.10per GPU-hour, the cheapest row to the dearest
Serverless: GPUs are billed by the second while a function runs, shown here as a GPU-hour. There is no instance to rent, and CPU and memory are billed separately.
As of , Modal lists 11 GPU models we track, from $0.59 per GPU-hour (NVIDIA T4, serverless, GPU only) to $7.10 (NVIDIA B300, serverless, GPU only).
| Website | modal.com |
|---|---|
| Pricing page | modal.com/pricing |
| Regions and tiers | No region or tier named in the rates below: one global rate card |
| Models tracked | 11 |
Price by GPU
As of , per GPU-hour: Modal’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 | Modal on-demand, per GPU-hour | Against the market (median rate card) |
|---|---|---|
| NVIDIA B300 | $7.10 GPU only captured Deploy ↗ | 21% below the median $8.99 · 26 providers 5 of 26 list lower · lowest Deep Infra $5.89 · compare |
| NVIDIA B200 | $6.25 GPU only captured Deploy ↗ | 10% below the median $6.94 · 40 providers 12 of 40 list lower · lowest Hostinger $4.50 from · compare |
| NVIDIA H200 | $4.54 GPU only captured Deploy ↗ | 1% below the median $4.56 · 56 providers 26 of 56 list lower · lowest Dataoorts $2.29 · compare |
| NVIDIA H100 SXM | $3.95 GPU only captured Deploy ↗ | 20% above the median $3.29 · 41 providers 25 of 41 list lower · lowest Cudo Compute $1.79 GPU only · compare |
| NVIDIA RTX PRO 6000 Blackwell | $3.03 GPU only captured Deploy ↗ | 38% above the median $2.20 · 42 providers 34 of 42 list lower · lowest Hostinger $0.65 from · compare |
| NVIDIA A100 80GB | $2.50 GPU only captured Deploy ↗ | 25% above the median $1.99 · 63 providers 42 of 63 list lower · lowest Yotta Labs $0.92 · compare |
| NVIDIA A100 40GB | $2.10 GPU only captured Deploy ↗ | 5% above the median $1.99 · 22 providers 13 of 22 list lower · lowest Trooper.AI $0.69 from · compare |
| NVIDIA L40S | $1.95 GPU only captured Deploy ↗ | 37% above the median $1.42 · 40 providers 31 of 40 list lower · lowest CloudRift $0.63 · compare |
| NVIDIA A10 | $1.10 GPU only captured Deploy ↗ | 10% below the median $1.22 · 9 providers 2 of 9 list lower · lowest Intelion Cloud $0.34 GPU only · compare |
| NVIDIA L4 | $0.80 GPU only captured Deploy ↗ | at the median $0.80 · 23 providers 11 of 23 list lower · lowest Hikube $0.28 GPU only · compare |
| NVIDIA T4 | $0.59 GPU only captured Deploy ↗ | 7% above the median $0.55 · 19 providers 10 of 19 list lower · lowest immers.cloud $0.24 · compare |
The same, in words
- Modal lists the NVIDIA B300 from $7.10 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 21% below the median rate card ($8.99 across 26 providers); 5 of the 26 providers we track list a lower on-demand rate, the lowest Deep Infra at $5.89 (Deep Infra’s rates, Modal vs Deep Infra).
- Modal lists the NVIDIA B200 from $6.25 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 10% below the median rate card ($6.94 across 40 providers); 12 of the 40 providers we track list a lower on-demand rate, the lowest Hostinger at $4.50 (Hostinger’s rates, Modal vs Hostinger).
- Modal lists the NVIDIA H200 from $4.54 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 1% below the median rate card ($4.56 across 56 providers); 26 of the 56 providers we track list a lower on-demand rate, the lowest Dataoorts at $2.29 (Dataoorts’s rates, Modal vs Dataoorts).
- Modal lists the NVIDIA H100 SXM from $3.95 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 20% above the median rate card ($3.29 across 41 providers); 25 of the 41 providers we track list a lower on-demand rate, the lowest Cudo Compute at $1.79 (Cudo Compute’s rates, Modal vs Cudo Compute).
- Modal lists the NVIDIA RTX PRO 6000 Blackwell from $3.03 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 38% above the median rate card ($2.20 across 42 providers); 34 of the 42 providers we track list a lower on-demand rate, the lowest Hostinger at $0.65 (Hostinger’s rates, Modal vs Hostinger).
- Modal lists the NVIDIA A100 80GB from $2.50 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 25% above the median rate card ($1.99 across 63 providers); 42 of the 63 providers we track list a lower on-demand rate, the lowest Yotta Labs at $0.92 (Yotta Labs’s rates, Modal vs Yotta Labs).
- Modal lists the NVIDIA A100 40GB from $2.10 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 5% above the median rate card ($1.99 across 22 providers); 13 of the 22 providers we track list a lower on-demand rate, the lowest Trooper.AI at $0.69 (Trooper.AI’s rates, Modal vs Trooper.AI).
- Modal lists the NVIDIA L40S from $1.95 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 7, 2026 (7-day change: none). Against the market: 37% above the median rate card ($1.42 across 40 providers); 31 of the 40 providers we track list a lower on-demand rate, the lowest CloudRift at $0.63 (CloudRift’s rates, Modal vs CloudRift).
- Modal lists the NVIDIA A10 from $1.10 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 10% below the median rate card ($1.22 across 9 providers); 2 of the 9 providers we track list a lower on-demand rate, the lowest Intelion Cloud at $0.34 (Intelion Cloud’s rates, Modal vs Intelion Cloud).
- Modal lists the NVIDIA L4 from $0.80 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 8, 2026 (7-day change: none). Against the market: at the median rate card ($0.80 across 23 providers); 11 of the 23 providers we track list a lower on-demand rate, the lowest Hikube at $0.28 (Hikube’s rates, Modal vs Hikube).
- Modal lists the NVIDIA T4 from $0.59 per GPU-hour on-demand (GPU only). The on-demand rate is unchanged since first read, Sep 22, 2026 (7-day change: none). Against the market: 7% above the median rate card ($0.55 across 19 providers); 10 of the 19 providers we track list a lower on-demand rate, the lowest immers.cloud at $0.24 (immers.cloud’s rates, Modal 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 T4GPU onlyserverless | $0.59 | captured | Deploy ↗ |
| NVIDIA L4GPU onlyserverless | $0.80 | captured | Deploy ↗ |
| NVIDIA A10GPU onlyserverless | $1.10 | captured | Deploy ↗ |
| NVIDIA L40SGPU onlyserverless | $1.95 | captured | Deploy ↗ |
| NVIDIA A100 40GBGPU onlyserverless | $2.10 | captured | Deploy ↗ |
| NVIDIA A100 80GBGPU onlyserverless | $2.50 | captured | Deploy ↗ |
| NVIDIA RTX PRO 6000 BlackwellGPU onlyserverless | $3.03 | captured | Deploy ↗ |
| NVIDIA H100 SXMGPU onlyserverless | $3.95 | captured | Deploy ↗ |
| NVIDIA H200GPU onlyserverless | $4.54 | captured | Deploy ↗ |
| NVIDIA B200GPU onlyserverless | $6.25 | captured | Deploy ↗ |
| NVIDIA B300GPU onlyserverless | $7.10 | captured | Deploy ↗ |
Ask an AI agent about Modal’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/modal/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/modal, an iframe, no script).
Compare Modal 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 10 shared GPUs
- Cerebrium 9 shared GPUs
- EmpirioLabs 9 shared GPUs
- Oracle Cloud (OCI) 9 shared GPUs
- RunPod 9 shared GPUs
- E2E Networks 8 shared GPUs
- GPU.ai 8 shared GPUs
- Sesterce 8 shared GPUs
- Vast.ai 8 shared GPUs
- Verda 8 shared GPUs
- Google Cloud 7 shared GPUs
- Hugging Face 7 shared GPUs
- Lium 7 shared GPUs
- Microsoft Azure 7 shared GPUs
- Civo 6 shared GPUs
- CoreWeave 6 shared GPUs
- HexGrid 6 shared GPUs
- Hyperstack 6 shared GPUs
- Jarvislabs 6 shared GPUs
- Koyeb 6 shared GPUs
- Lightning AI 6 shared GPUs
- Nebius 6 shared GPUs
- Northflank 6 shared GPUs
- Seeweb 6 shared GPUs
- Barrack AI 5 shared GPUs
- Beam 5 shared GPUs
- Crusoe 5 shared GPUs
- Gcore 5 shared GPUs
- Geodd 5 shared GPUs
- Hikube 5 shared GPUs
- Lambda 5 shared GPUs
- Lyceum 5 shared GPUs
- OpenRelay 5 shared GPUs
- Paperspace 5 shared GPUs
- Runware 5 shared GPUs
- Yotta Labs 5 shared GPUs
- Baseten 4 shared GPUs
- Daytona 4 shared GPUs
- Deep Infra 4 shared GPUs
- fal 4 shared GPUs
- FarmGPU 4 shared GPUs
- FPT AI Factory 4 shared GPUs
- Hostinger 4 shared GPUs
- immers.cloud 4 shared GPUs
- Limestone Networks 4 shared GPUs
- Massed Compute 4 shared GPUs
- Neysa 4 shared GPUs
- OVHcloud 4 shared GPUs
- packet.ai 4 shared GPUs
- Tata Communications 4 shared GPUs
- Together AI 4 shared GPUs
- airgpu 3 shared GPUs
- Bitdeer AI 3 shared GPUs
- CloudGPU 3 shared GPUs
- Cudo Compute 3 shared GPUs
- Dataoorts 3 shared GPUs
- Denvr Dataworks 3 shared GPUs
- Elice Cloud 3 shared GPUs
- Fireworks AI 3 shared GPUs
- HPC-AI.COM 3 shared GPUs
- Hyperbolic 3 shared GPUs
- Inferless 3 shared GPUs
- Infomaniak 3 shared GPUs
- QuantaCloud 3 shared GPUs
- Replicate 3 shared GPUs
- Selectel 3 shared GPUs
- Servercore 3 shared GPUs
- STACKIT 3 shared GPUs
- VESSL AI 3 shared GPUs
- Airon 2 shared GPUs
- Atlas Cloud 2 shared GPUs
- Bamboozle Web Services 2 shared GPUs
- Canopy Wave 2 shared GPUs
- centron 2 shared GPUs
- Clore.ai 2 shared GPUs
- Cloud.ru Evolution 2 shared GPUs
- CloudRift 2 shared GPUs
- Enverge 2 shared GPUs
- FlexAI 2 shared GPUs
- FluidCore 2 shared GPUs
- GMI Cloud 2 shared GPUs
- Intelion Cloud 2 shared GPUs
- Leafcloud 2 shared GPUs
- MimicPC 2 shared GPUs
- RunComfy 2 shared GPUs
- SynpixCloud 2 shared GPUs
- Taiga Cloud (Northern Data Group) 2 shared GPUs
- Thunder Compute 2 shared GPUs
- Trooper.AI 2 shared GPUs
- Yandex Cloud 2 shared GPUs
Data updated: