Modal
Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.
On-demand GPU instances billed by the minute with no egress fees, from a company that also builds the hardware. Scales from one GPU to eight per instance.
Usage-based plans are shown as Metered and are excluded from stack totals.
| Category | Infra |
|---|---|
| Company | Lambda |
| Free plan | No |
| Starting price | Usage-based |
| Top plan | Not verified |
| Pricing model | usage |
| API | Not verified |
| Open weights | Not verified |
| Commercial use | Not verified |
| Rating | Not rated — we do not publish scores we cannot source. |
Last verified: 22 Aug 2026
Pricing source: lambda.com
Listing status: Unclaimed, verified
Are you the owner of Lambda? Claim this listing.
Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.
Per-second GPU rental across Community and Secure Cloud tiers, plus serverless inference workers.
Custom silicon delivering very high tokens-per-second on open models.
Run open models locally on your own machine.
One API key, hundreds of models, automatic failover.
Managed Ray for distributed training and inference, either hosted or inside your own cloud account.