Create a provider connection#

  1. Open Settings → AI Platform.
  2. Enter the connection name, protocol, provider and endpoint. Add region/residency metadata where relevant.
  3. Provide the managed credential if the provider requires one. The form does not display stored secrets back to users.
  4. Create the connection and use Test. Complete reauthentication when required.
  5. If the test fails, inspect endpoint/protocol compatibility, credentials, network rules and provider availability before adding models.

The protocol selector includes OpenAI-compatible, Anthropic Messages, Azure OpenAI, Amazon Bedrock, Google Gemini and Google Vertex adapters. Use the endpoint and credential form supported by the selected protocol, then test it; a selectable adapter name is not proof that a particular endpoint or account is configured correctly.

Configure a provider connection, then register a model and establish a workspace policy. This example has no configured connection or available model.
Configure a provider connection, then register a model and establish a workspace policy. This example has no configured connection or available model. View full size ↗

Register and test a model#

  1. Choose the connection and enter a display name and exact provider model identifier.
  2. Create the model. The UI creates it disabled, with text, streaming and tool capabilities requested.
  3. Run the model conformance test. It checks the supported response/tool behavior against the provider.
  4. Inspect the outcome. Passing conformance enables the model; a failed test leaves it unavailable.
  5. Verify the model becomes available to the intended policy and user scope.

Understand the default-policy action#

The page’s default-policy action selects an enabled model when possible and includes the configured models in its allowlist. Its default tools are read-oriented: resource get/list/describe, pod logs, overview and Prometheus queries. It does not automatically grant every mutating AI tool.

Default policy fieldCurrent UI value
Requests per minute / day30 / 1000
Tokens per day1,000,000
Maximum concurrent4
Usage retention90 days
FallbackDisabled, with no fallback model list.
Allowed roles/clusters/residenciesWildcard defaults; review before broad use.

These are defaults created by this UI action, not purchased capacity guarantees. Use the administrative API for policy settings that are not available in the console.

Monitor and revoke#

Review requests, token use and cost metadata in the usage area. Cost depends on configured price metadata and is not a replacement for the provider’s bill. Revoke a connection when it is retired; the backend disables its models. Retest after changing a provider or model configuration.