| Field | Value |
|---|---|
| Provider | OVHcloud |
| Category | inference |
| Offer status | available |
| Deal type | free |
| What is free | Anonymous, unauthenticated inference against the AI Endpoints model catalogue at 2 requests per minute, per IP and per model — no API key, no account, no signup of any kind. Verbatim: "Anonymous: 2 requests per minute, per IP and per model." |
| Access barrier | none |
| How you get a credential | unknown (inferred from the access barrier) |
| Agent-usable | True |
| Evidence | documented |
| Confidence | verified |
| Last verified | 2026-09-16 |
| Source | https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started |
| Caveats | 2 req/min is a trickle — this is for evaluation and fallback, not workload. Exceeding it returns 429; an API access key raises it to 400 req/min per PCI project per model. RATE-LIMITED PER IP, WHICH IS THE TRAP FOR AGENT FLEETS: every agent behind one egress address shares the 2/min, so a shared-NAT caller will see 429s that look like an outage and are not (this catalog has hit exactly that failure against NASA's DEMO_KEY). Third parties report "$200 in trial credits"; that figure is NOT stated first-party and this row does not carry it. NOTE ON THE SOURCE URL: the same path WITH a trailing slash serves a 404 body under HTTP 200 — a soft 404. The URL above, without it, is the live document. |
No measured example — this row is evidence: documented: it states what the provider's own page advertised on the date shown, and this worker holds no credential to call it. The provider's documentation is the source: https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started
Rendered 2026-09-16 03:07 UTC. Machine-readable: ai-deals.json.