connections
GET /v1/inference/deployments
The organisation's model deployments and what is actually serving.
Uthibitishaji
Tuma ufunguo wa API kama tokeni ya kubeba. Sehemu hii ya mwisho haitaji ruhusa maalum katika maelezo, kwa hivyo ipe ufunguo wako kiwango cha chini kabisa kinachohitajika na uangalie jibu badala ya kukisia.
Endpoint hii haichukui kitambulisho cha shirika. Ufunguo wako tayari unalitambua shirika linalohusika, na jibu limewekewa kikomo kwa shirika hilo pekee.
Jaribu
Badilisha chochote kilicho ndani ya mabano ya pembe na maadili yako mwenyewe, na kishikiliaji cha ufunguo na ufunguo kutoka kwa dashibodi yako.
curl -X GET https://api.zinndigital.com/v1/inference/deployments \
-H "Authorization: Bearer zdk_live_…"Umeingia kwenye akaunti? Dashibodi yako ya kiweko cha API inajaza kitambulisho chako halisi cha shirika na ufunguo wako mwenyewe, na kuendesha ombi dhidi ya API ya moja kwa moja ili uweze kuona jibu halisi. Fungua sehemu hii ya mwisho (endpoint) kwenye konsole ya API
Maelezo
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.
Majibu
| Jina | Aina | Inayohitajika | Kilicho hiki |
|---|---|---|---|
deployments | InferenceDeployment[] | Ndiyo | — |
Hitilafu ambazo mwisho huu unaweza kurudisha
401 · 429