GET /v1/inference/deployments

Authentication

Send an API key as a bearer token. This endpoint does not state a specific permission in the specification, so give your key the least it needs and check the response rather than assuming.

This endpoint takes no organisation id. Your key already identifies the organisation it belongs to, and the response is scoped to it.

Try it

Replace anything in angle brackets with your own values, and the key placeholder with a key from your dashboard.

curl -X GET https://api.zinndigital.com/v1/inference/deployments \
  -H "Authorization: Bearer zdk_live_…"

Signed in? The API console in your dashboard fills in your real organisation id and your own key, and runs the request against the live API so you can see the actual response. Open this endpoint in the API console

Details

Model endpoints on the customer's own inference account. ⛔ `replicas` is what was **asked for** and `ready_replicas` is what is **serving**. A screen showing only the first reports a healthy deployment that is answering nothing. `ready_replicas` is `null` when the provider did not report readiness at all — which is not the same as zero. `state` includes `degraded` (some replicas up, some not) and `deleting` (being torn down, and possibly still holding GPUs). Neither is rounded onto a neighbour: a `degraded` deployment reported as `running` hides missing capacity, and a `deleting` one reported as `stopped` implies it has stopped costing money.

Response

Errors this endpoint can return

401 · 429