Skip to content

InteractionProcessCredential

A model provider API key a run was started with (the key itself is never returned). For each call the run tries these keys in priority order, then your tenant’s model keys, and moves on to the next when one fails authentication or hits a quota.

Kind: an object, used in responses.

Every field is present in a response; empty ones are null.

FieldTypeDescription
providerstringThe model provider the key is for, as given when the run started: a model-key provider name such as Anthropic, OpenAi or Qwen, or an inline model’s credentialProvider.
baseUrlstring | nullThe endpoint to call with this key, such as a regional Qwen host or an Azure resource. Null: the provider’s default.
modelNameOverridesmap<string, string> | nullCatalogue model names mapped to the model or deployment id this key’s endpoint uses for them, such as an Azure deployment name. Null or empty: the catalogue’s ids are used as they are.
credentialIdstringYour own id for the key. The run’s token usage and credential failures carry it, so you can tell which key served or failed a call.
isOwnLicensebooleanTrue for a key of your own, which the provider bills you for directly. Only such keys are used.
priorityintegerThe order keys for the same provider are tried in: lowest first.
{
"provider": "...",
"baseUrl": "...",
"modelNameOverrides": {
"key": "..."
},
"credentialId": "...",
"isOwnLicense": false,
"priority": 0
}