RunPod
Per-second GPU rental across Community and Secure Cloud tiers, plus serverless inference workers.
Run thousands of community models by the second — image, video, audio, text. No subscription at all.
Usage-based plans are shown as Metered and are excluded from stack totals.
| Category | Infra |
|---|---|
| Company | Replicate |
| Free plan | No |
| Starting price | Usage-based |
| Top plan | Not verified |
| Pricing model | usage |
| API | Yes |
| Open weights | Not verified |
| Commercial use | Not verified |
| Rating | Not rated — we do not publish scores we cannot source. |
Last verified: 17 Aug 2026
Pricing source: replicate.com
Listing status: Unclaimed, verified
Are you the owner of Replicate? Claim this listing.
Per-second GPU rental across Community and Secure Cloud tiers, plus serverless inference workers.
Model deployment with fast cold starts and per-minute billing, so idle time costs nothing.
Custom silicon delivering very high tokens-per-second on open models.
Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.
Run open models locally on your own machine.
Managed Ray for distributed training and inference, either hosted or inside your own cloud account.