Databricks SDK for JavaScript
    Preparing search index...

    Interface ModelProviderServiceConfig

    Behavioral configuration for a ModelProviderService: provider authentication and provider-specific fields, the catalog of models this provider service can route to, and the passthrough policy that governs how request headers, query parameters, and unmanaged subpaths cross the trust boundary to the upstream provider.

    interface ModelProviderServiceConfig {
        allowAllTargets?: boolean;
        forwardHeaders?: boolean;
        forwardQueryParameters?: boolean;
        forwardUnmanagedPaths?: boolean;
        inferenceTable?: InferenceTableConfig;
        provider?:
            | {
                $case: "openai";
                openai: ModelProviderServiceConfig_OpenAiProviderConfig;
            }
            | {
                $case: "azureOpenai";
                azureOpenai: ModelProviderServiceConfig_AzureOpenAiProviderConfig;
            }
            | {
                $case: "anthropic";
                anthropic: ModelProviderServiceConfig_AnthropicProviderConfig;
            }
            | {
                $case: "amazonBedrock";
                amazonBedrock: ModelProviderServiceConfig_AmazonBedrockProviderConfig;
            }
            | {
                $case: "custom";
                custom: ModelProviderServiceConfig_CustomProviderConfig;
            }
            | {
                $case: "microsoftFoundry";
                microsoftFoundry: ModelProviderServiceConfig_MicrosoftFoundryProviderConfig;
            }
            | {
                $case: "geminiEnterprise";
                geminiEnterprise: ModelProviderServiceConfig_GeminiEnterpriseProviderConfig;
            };
        providerType?: ModelProviderServiceConfig_ExternalModelProviderType;
        rateLimits?: RateLimit[];
        targets?: ModelProviderServiceConfig_ModelTargetConfig[];
    }
    Index

    Properties

    allowAllTargets? forwardHeaders? forwardQueryParameters? forwardUnmanagedPaths? inferenceTable? provider? providerType? rateLimits? targets?

    Properties

    allowAllTargets?: boolean

    When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable. Defaults to false.

    forwardHeaders?: boolean

    Whether to forward incoming HTTP headers to the upstream provider. Defaults to false and is configured for the entire provider service, not per request. Upstream authentication is configured separately in the provider-specific configuration.

    forwardQueryParameters?: boolean

    Whether to forward incoming query parameters to the upstream provider. Defaults to false and is configured for the entire provider service, not per request.

    forwardUnmanagedPaths?: boolean

    Whether to proxy paths that AI Gateway does not recognize as configured provider-native API types. Defaults to false. When true, these paths are forwarded unchanged to the upstream provider. When false, only recognized API paths are served. Enabling this broadens the upstream API surface exposed through the provider service.

    inferenceTable?: InferenceTableConfig

    Payload logging configuration for requests sent directly to this provider service. Requests routed through a model service are captured by that model service's inference table instead.

    provider?:
        | {
            $case: "openai";
            openai: ModelProviderServiceConfig_OpenAiProviderConfig;
        }
        | {
            $case: "azureOpenai";
            azureOpenai: ModelProviderServiceConfig_AzureOpenAiProviderConfig;
        }
        | {
            $case: "anthropic";
            anthropic: ModelProviderServiceConfig_AnthropicProviderConfig;
        }
        | {
            $case: "amazonBedrock";
            amazonBedrock: ModelProviderServiceConfig_AmazonBedrockProviderConfig;
        }
        | {
            $case: "custom";
            custom: ModelProviderServiceConfig_CustomProviderConfig;
        }
        | {
            $case: "microsoftFoundry";
            microsoftFoundry: ModelProviderServiceConfig_MicrosoftFoundryProviderConfig;
        }
        | {
            $case: "geminiEnterprise";
            geminiEnterprise: ModelProviderServiceConfig_GeminiEnterpriseProviderConfig;
        }

    Provider-specific configuration. Exactly one variant must be set, and it must match provider_type. Supply secret values in the nested plaintext field. Secret values are stored encrypted and omitted from responses; non-secret configuration fields are returned as stored.

    (-- Declarative tooling must treat plaintext as write-only because it never round-trips on reads. --)

    (-- Secrets are persisted as the encrypted credential of a per-MPS UC SchemaConnection (CONNECTION_HTTP_BEARER). The auto-minted SchemaConnection is user-owned but hidden from the user, so it is not surfaced as a connection they manage directly even though the credential could in principle be changed out of band. --)

    (-- Field-behavior on the per-provider config fields: (google.api.field_behavior) = OPTIONAL everywhere on the *DirectConfig descendants, with Create-time requirements enforced in the validator. Proto-level REQUIRED is deliberately not used per the proto-required-vs-update-mask guardrail: REQUIRED would reject sparse Update requests that legitimately omit a field whose value is unchanged, breaking AIP-134 partial-Update. The user-facing javadoc on each field states which fields are required on Create. --)

    providerType?: ModelProviderServiceConfig_ExternalModelProviderType

    External model provider. Required on Create and immutable thereafter. Set the matching provider-specific configuration, such as openai, azure_openai, or amazon_bedrock.

    rateLimits?: RateLimit[]

    Rate limits for requests sent directly to this provider service. Requests routed through a model service use that model service's rate limits instead.

    targets?: ModelProviderServiceConfig_ModelTargetConfig[]

    Models and provider-native API types exposed by this provider service. Each entry must include at least one native_api_types value. When allow_all_targets is false, at least one entry is required and model service destinations can reference only listed models. When allow_all_targets is true, any upstream model is routable; entries in this list provide API-type metadata without restricting other models.

    Settings

    Member Visibility

    On This Page

    Properties