Skip to main content

Get LLM provider

GET https://api.rollstack.com/public/v1/organization/llm-provider

The organization's custom LLM provider, without its credentials. Only owners, and members an owner allowed to manage the AI provider, may call it.

Requires the organization:read scope.

Operation ID: getLLMProvider.

Response 200

Success

application/json

  • id (string, required): Unique identifier for the organization's LLM provider. It stays the same when you replace the provider with setLLMProvider; setting one up again after deleteLLMProvider gives a new one.
  • type (string, required): The provider the organization's slides agent runs on, instead of Rollstack's own AI providers: anthropic (the Anthropic API), openai (the OpenAI API), azure_foundry (an Azure AI Foundry resource), amazon_bedrock (Amazon Bedrock in an AWS account) or google_vertex_ai (Vertex AI in a Google Cloud project). Insights don't use it: they run on the organization's llmProvider, from getOrganization. One of anthropic, openai, azure_foundry, amazon_bedrock, google_vertex_ai.
  • auth (string, required): How Rollstack signs in to the provider. With apiKey, it uses a secret saved with the provider: an API key or, on Google Vertex AI, a service account key. With oidc, the setup is keyless: your provider trusts short-lived tokens from Rollstack's OpenID Connect issuer for your organization, so no secret is saved. One of apiKey, oidc.
  • hasCredentials (true, required): Whether the provider has saved credentials: always true. Its secrets, apiKey or privateKey, are never returned, not even in settings: to change them, send the whole setup again with setLLMProvider.
  • settings (object, required): The provider's saved setup without its secrets: the credentials it was last saved with, as in the setLLMProvider body, minus apiKey and privateKey. It contains auth and, depending on type: dataResidency (OpenAI); resourceName and models (Azure AI Foundry); region, dataLocation and models (Amazon Bedrock); or projectId, region and models, plus clientEmail with a service account key (Google Vertex AI). A keyless setup also contains its ids, such as tenantId and clientId, or roleArn.
  • updatedAt (string (date-time), required): When the provider was last saved, with setLLMProvider or in the app. Recording or clearing a failure doesn't change it.
  • updatedBy (object or null, required): The member who last saved the provider, with setLLMProvider or in the app. When failure is set, Rollstack notifies them, or the organization's owners if they're no longer an active member. null if that user's account no longer exists.
    • name (string or null, required): The name of the member who last saved the provider, as shown in Rollstack.
    • email (string, required): The email address of the member who last saved the provider.
  • failure (string or null, required): Why the slides agent's calls to the provider are failing, when only a change on your provider's side can fix it. null while calls work. key_invalid: the provider doesn't accept the API key or the keyless sign-in. forbidden: the key or sign-in isn't allowed to use failedModel. model_not_found: failedModel isn't available to the account; on Azure AI Foundry, it isn't deployed under its own name, and on Amazon Bedrock or Google Vertex AI, it isn't enabled. out_of_credit: the provider account is out of credit. When it's set, Rollstack notifies the member in updatedBy, or the owners if they're no longer an active member. It's cleared once a call to failedModel works again or the provider is saved again. One of key_invalid, forbidden, model_not_found, out_of_credit.
  • failedAt (string (date-time) or null, required): When a slides agent call to the provider first failed with the current failure. null while calls work.
  • failedModel (string or null, required): The model whose call failed, such as claude-haiku-5-5. Until the provider is saved again, only a working call to this model clears failure, so a failing fast model stays flagged even while the smart one works. null while calls work.