ai
POST /v1/ai/credentials/{credentialId}/test
Test a stored AI provider key now.
Ìfàṣẹ́pọ̀
Fi bọ́ọ̀lù (bearer token) ranṣẹ gẹ́gẹ́ bí kọ́kọ́rọ́ API. Kọ́kọ́rọ́ náà gbọ́dọ̀ ní ìyọ̀ǹda billing.payment.manage; a ó kọ̀ ọ́ silẹ pẹlu 403, kii ṣe 404, ti kọ́kọ́rọ́ náà kò bá ní i.
Ojú abánisọ̀rọ̀ yìí kò gba id ajọ kankan. Kọ́kọ́rọ́ rẹ ti mọ ajọ ti o jẹ ti e, a o si fèsì nipa rẹ̀.
Gbiyanju rẹ
Rọ́pọ̀ èyíkéyìí nínú àwọn àmì ìtọ́ka < > pẹ̀lú iye tirẹ̀, àti àmì ìdánimọ̀ bọ́tìnnì náà pẹ̀lú bọ́tìnnì kan láti inú dásibọ̀ọ̀dù rẹ.
curl -X POST https://api.zinndigital.com/v1/ai/credentials/{credentialId}/test \
-H "Authorization: Bearer zdk_live_…"Ṣé o ti wọlé? Iwọ̀n api ní nú ìgbékalẹ̀ rẹ kún id àjọ gidi rẹ ati bọtini tirẹ, o si nṣiṣẹ ibeere na lòdì si api gidi ki o le rii esi gidi na. Ṣí ojú abáná yìí sílẹ̀ nínú kọnsólù API
Àwọn kúlẹ̀kúlẹ̀
Runs a **real, tiny completion with our own prompts and tool format** on the key — not the free authentication probe. ⚖️ The owner's requirement, verbatim: *"it must test it works with our system and prompts."* Authenticating and *working with our prompts* are different claims, and a screen showing only the first as a green tick is a control that cannot see the failure it exists to catch. Costs a fraction of a cent on the customer's own key, which is why it is only ever run on save, weekly, or when a person presses the button. Requires `billing.payment.manage`.
Àwọn ìpìlẹ̀
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
credentialId (path) | Uuid | Bẹẹni | — |
Idahun
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
ok | boolean | Bẹẹni | — |
exercised_prompt | boolean | Bẹẹni | ⭐ Whether a **real call with our own prompts** was made. `false` means we proved only that the key authenticates — a narrower claim a screen showing just "working" would erase,… |
detail | string | Bẹẹkọ | — |
model | string | Bẹẹkọ | — |
latency_ms | integer | Bẹẹkọ | — |
state | string<untested, working, broken> | Bẹẹni | — |
Awọn aṣiṣe ti ibudo ipari yii le da pada
401 · 403 · 404 · 429