Modal is under the market median on 4 of its 11 GPUs today.
Modal is a serverless GPU platform that lets developers run Python functions, jobs and inference endpoints on NVIDIA GPUs with per-second billing and scale-to-zero.
At a glance · prices collected Nov 8, 2026
What's good about Modal
- Serverless model removes idle-instance costs
- Per-second billing across the full GPU range
- Strong fit for inference, batch jobs and ML pipelines
Modal GPU prices
11 GPU models across 11 configurations. Rank compares Modal's cheapest on-demand listing for each GPU with every provider's cheapest.
| GPU | Modal | -60%median+100% | Rank | vs. median | Report |
|---|---|---|---|---|---|
| H100 SXM 1× | $3.95/hr | #36 of 57 providers | +23% | ||
| A100 SXM 1× | $2.50/hr | #33 of 43 providers | +57% | ||
| H200 1× | $4.54/hr | #22 of 43 providers | at median | ||
| L40S 1× | $1.95/hr | #35 of 41 providers | +79% | ||
| RTX PRO 6000 1× | $3.03/hr | #36 of 41 providers | +41% | ||
| B200 1× | $6.25/hr | #11 of 33 providers | -17% | ||
| HGX B300 1× | $7.10/hr | #9 of 31 providers | -16% | ||
| L4 1× | $0.80/hr | #10 of 22 providers | -3% | ||
| A100 PCIE 1× | $2.10/hr | #12 of 15 providers | +83% | ||
| A10 1× | $1.10/hr | #6 of 14 providers | -12% | ||
| Tesla T4 1× | $0.59/hr | #13 of 14 providers | +57% |
What a run costs on Modal
24 hours at today's cheapest listing for each GPU, at the size it is listed.
1× H100 SXM for 24 hours
At $3.95/GPU-hr
$94.78
$17.98 over the market median rate
1× A100 SXM for 24 hours
At $2.50/GPU-hr
$59.96
$21.80 over the market median rate
1× H200 for 24 hours
At $4.54/GPU-hr
$108.95
Same as at the market median rate
The market median is every provider's cheapest on-demand price for that GPU.
Billing & terms
- Per-Second GPU Billing
- Charged per second of GPU runtime, with scale-to-zero when idle
- Free Tier
- Monthly free credits for experimentation and personal projects
- Team and Enterprise Plans
- Volume commitments and enterprise support for production deployments
- Regions
- Multi-region availability across North America and Europe
- Support
- Documentation, community forum, and enterprise support for paid plans
Watch out for
- Long-running, fixed-instance training is not the primary use case
- Cold starts and storage limits require some application design
- No bare-metal access; workloads run inside Modal's runtime
Features
- Serverless GPUs
- Run Python functions on NVIDIA GPUs without provisioning instances; cold starts in seconds
- Per-Second Billing
- Pay for actual GPU runtime at sub-minute granularity, with scale-to-zero by default
- Container-Native
- Define environments in code, with automatic image building and caching
- Wide GPU Catalog
- From T4 and L4 through A100, L40S, H100, H200 and B200
Getting started
Step 1
Install the SDK
Run `pip install modal` and authenticate via the CLI
Step 2
Define a function
Decorate a Python function with the desired GPU and image specification
Step 3
Run or deploy
Invoke locally or deploy as a long-lived endpoint or scheduled job
Where this page's facts come from
- GPU prices
- Modal (modal.com) · last collected Nov 8, 2026
- Profile
- Reviewed May 8, 2026
- Method
- How we collect and check prices
Frequently Asked Questions
What GPU types does Modal offer?
Modal offers various GPU types including A100 PCIE, Tesla T4, A100 SXM, H100 SXM, H200, A10, HGX B300, L40S, B200, L4, RTX PRO 6000. Check the pricing table above for current availability and pricing.
How do I get started with Modal?
Install the SDK, Define a function, Run or deploy
What are Modal's main advantages?
Modal's main advantages include: Serverless model removes idle-instance costs, Per-second billing across the full GPU range, Strong fit for inference, batch jobs and ML pipelines.
What are Modal's limitations?
Modal's main limitations include: Long-running, fixed-instance training is not the primary use case, Cold starts and storage limits require some application design, No bare-metal access; workloads run inside Modal's runtime.
Compare Providers
Find the best prices for the same GPUs and models from other providers · All Modal alternatives, ranked →
All Modal Comparisons
The weekly price report
One email every Monday with the week's notable GPU and LLM API price moves, plus occasional product news. No spam.