Baseten vs Modal
- GPUs
- 6 11
- Cheapest GPU
- $0.63/hr $0.59/hr
- Price wins
- 0/5 5/5
Modal is cheaper on all 5 GPUs both rent. Modal carries 5 more GPUs.
Runs dedicated model inference billed per minute of GPU time, plus pre-optimised model APIs billed per token.
Best for: Production inference for custom models
Serverless GPU platform where code runs as functions for inference, batch jobs and training, billed per second with no commitments.
Best for: Serverless inference and batch jobs
Price by GPU
The 5 GPUs both rent. Cheapest live rate per GPU-hour, most powerful first. The cheaper side is in purple.
| GPU | Baseten | Modal | Gap |
|---|---|---|---|
| NVIDIA B200 SXM 180GB | $9.98/hr | $6.25/hr | 60% |
| NVIDIA H100 SXM5 80GB | $6.50/hr | $3.95/hr | 65% |
| NVIDIA A100 SXM4 80GB | $4.00/hr | $2.50/hr | 60% |
| NVIDIA L4 24GB | $0.85/hr | $0.80/hr | 6% |
| NVIDIA T4 16GB | $0.63/hr | $0.59/hr | 7% |
Prices last checked: Baseten 1 Oct 2026, Modal 1 Oct 2026.
Only on one side
Company facts
| Fact | Baseten | Modal |
|---|---|---|
| Headquarters |  San Francisco, CA | New York City, United States |
| Type | GPU cloud | GPU cloud |
| GPUs priced | 6 | 11 |
| Fastest GPU | NVIDIA B200 SXM 180GB | NVIDIA B200 SXM 180GB |
| Services | Dedicated model inference, pre-optimised model APIs, training (Loops SDK), self-hosted deployment | Serverless GPU compute, inference, batch jobs, training, sandboxes |
| Pricing models | Per-minute GPU compute, per-token for model APIs | Pay-per-second, no commitments |
Compliance
Frameworks each provider states it holds, linked to its own statement. Not published means we found no statement, not that the provider fails it. Check the scope with the provider.
Pick your provider
Questions
- What is the difference between Baseten and Modal?
- Baseten: Runs dedicated model inference billed per minute of GPU time, plus pre-optimised model APIs billed per token. Modal: Serverless GPU platform where code runs as functions for inference, batch jobs and training, billed per second with no commitments.
- Is Baseten cheaper than Modal?
- Modal is cheaper on all 5 GPUs both rent. Modal carries 5 more GPUs.
- How much does a NVIDIA B200 SXM 180GB cost on Baseten and Modal?
- Baseten charges $9.98 per GPU-hour and Modal charges $6.25 per GPU-hour, the cheapest live rate on each.
- Which GPUs can I rent on both Baseten and Modal?
- 5 GPUs, including NVIDIA B200 SXM 180GB, NVIDIA H100 SXM5 80GB, NVIDIA A100 SXM4 80GB, NVIDIA L4 24GB, NVIDIA T4 16GB.
- How are these prices compared?
- Each figure is the cheapest live rate per GPU-hour for that GPU. We use on-demand pricing where a provider sells it and fall back to community or reserved terms, labelled, where that is all they sell. Spot capacity is left out because it can be reclaimed. Rates are refreshed by our daily ingest.
How we define a live price: methodology.
