Anyscale
Managed Ray for distributed training and inference, either hosted or inside your own cloud account.
One API key, hundreds of models, automatic failover. The easiest way to compare models on price before committing.
Usage-based plans are shown as Metered and are excluded from stack totals.
| Category | Infra |
|---|---|
| Company | OpenRouter |
| 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| Rating | Not rated — we do not publish scores we cannot source.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: 13 Nov 2026
Pricing source: openrouter.ai
Listing status: Unclaimed, verified
Are you the owner of OpenRouter? 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.
Custom silicon delivering very high tokens-per-second on open models.
On-demand GPU instances billed by the minute with no egress fees, from a company that also builds the hardware.