Anyscale
Managed Ray for distributed training and inference, either hosted or inside your own cloud account.
Custom silicon delivering very high tokens-per-second on open models. Free tier for testing, metered above it.
Usage-based plans are shown as Metered and are excluded from stack totals.
| Category | Infra |
|---|---|
| Company | Groq |
| Free plan | Yes |
| Starting price | Free |
| Top plan | Not verified |
| Pricing model | free and 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| Rating | Not rated — we do not publish scores we cannot source.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: groq.com
Listing status: Unclaimed, verified
Are you the owner of Groq? Claim this listing.
Managed Ray for distributed training and inference, either hosted or inside your own cloud account.
Model deployment with fast cold starts and per-minute billing, so idle time costs nothing.
Token-metered serving for open-weight models at some of the lowest published rates, with no contracts or upfront cost.
Low-latency open-model serving with tuned deployments and function calling.
On-demand GPU instances billed by the minute with no egress fees, from a company that also builds the hardware.
Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.