> ## Documentation Index > Fetch the complete documentation index at: https://ngrok.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Apply a partial update to an AI Gateway provider. The providerId is immutable after # Update an AI Gateway provider ## OpenAPI ````yaml openapi/ai-gateway.yaml PATCH /providers/{id} openapi: 3.0.3 info: title: AI Gateway APIs version: 0.1.0 description: | Control-plane HTTP APIs served by the ai-gateway-control service. servers: - url: https://api.ngrok.ai security: - bearerAuth: [] tags: - name: AI Gateway Access Key Configurations description: Manage reusable access key configurations (scope and routing rules). - name: AI Gateway Access Keys description: Manage ngrok-managed access keys associated with AI Gateway endpoints. - name: AI Gateway Configuration description: >- Manage per-account AI Gateway configuration (timeouts, token caps, metadata). - name: AI Gateway API Keys description: Manage customer-facing AI Gateway API Keys. - name: AI Gateway Credits description: Purchase AI Gateway credits via Stripe Checkout. - name: AI Gateway Providers description: Manage AI Gateway providers and the models they expose. - name: AI Gateway Custom Providers description: Manage custom AI Gateway providers and the models they expose. - name: AI Gateway Provider Keys description: Manage provider keys attached to AI Gateway managed access keys. - name: AI Gateway Usage description: >- Read-only AI Gateway usage events and aggregated usage overview for the authenticated account. paths: /providers/{id}: parameters: - $ref: '#/components/parameters/AIGatewayProviderID' patch: tags: - AI Gateway Providers summary: Update an AI Gateway provider description: > Apply a partial update to an AI Gateway provider. The providerId is immutable after creation. Models follow REST PATCH-array semantics: omit the field to leave existing models alone, send an empty array to clear all models, or send a full list to replace the existing set. operationId: UpdateAIGatewayProvider requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AIGatewayProviderUpdate' responses: '200': description: The updated AI Gateway provider. content: application/json: schema: $ref: '#/components/schemas/AIGatewayProvider' default: $ref: '#/components/responses/Error' components: parameters: AIGatewayProviderID: name: id in: path required: true description: Unique identifier for an AI Gateway provider. schema: type: string schemas: AIGatewayProviderUpdate: type: object additionalProperties: false properties: name: type: string nullable: true minLength: 1 maxLength: 255 description: User-friendly label for this provider. baseUrl: type: string minLength: 1 maxLength: 2048 description: >- Base URL of the provider's API endpoint. Cannot be cleared (every provider has one). metadata: type: string nullable: true maxLength: 4096 description: Arbitrary user-defined metadata for this provider. supportedApiSurfaces: type: array nullable: true description: API surfaces supported by this provider. items: $ref: '#/components/schemas/SupportedAPISurface' models: type: array nullable: true description: > Full replacement set for the models attached to this provider. Omit the field to leave existing models alone, send an empty array to clear all models, or send a full list to replace the existing set. items: $ref: '#/components/schemas/AIGatewayProviderModelCreate' AIGatewayProvider: type: object additionalProperties: false required: - id - uri - providerId - name - baseUrl - createdAt - updatedAt - createdBy - lastUpdatedBy properties: id: type: string description: Unique identifier for this provider. uri: type: string description: URI of this AI Gateway Provider API resource. providerId: type: string description: >- Provider identifier used as the address segment in model strings (for example "internal-vllm"). name: type: string description: User-friendly label for this provider. baseUrl: type: string description: Base URL of the provider's API endpoint. metadata: type: string description: Arbitrary user-defined metadata for this provider. createdAt: type: string format: date-time description: Timestamp when the provider was created. updatedAt: type: string format: date-time description: Timestamp when the provider was last updated. createdBy: $ref: '#/components/schemas/Ref' lastUpdatedBy: $ref: '#/components/schemas/Ref' supportedApiSurfaces: type: array description: API surfaces supported by this provider. items: $ref: '#/components/schemas/SupportedAPISurface' models: type: array description: Models exposed by this provider. items: $ref: '#/components/schemas/AIGatewayProviderModel' SupportedAPISurface: type: object additionalProperties: false required: - format properties: format: type: string description: | The API format this surface conforms to (for example "openai" or "anthropic"). Validated against ngrok's known formats at runtime. surface: type: string description: | The specific API surface within the format (for example "chat-completions", "responses", or "messages"). Validated against ngrok's known surfaces at runtime. supportedParams: type: array description: Top-level request body parameters supported by this surface. items: $ref: '#/components/schemas/SupportedAPISurfaceParam' AIGatewayProviderModelCreate: type: object additionalProperties: false required: - modelId properties: modelId: type: string minLength: 1 maxLength: 255 description: Model identifier (for example "llama-3"). Ref: type: object additionalProperties: false required: - id - uri properties: id: type: string description: Resource identifier. uri: type: string description: URI for locating the resource. AIGatewayProviderModel: type: object additionalProperties: false required: - id - modelId properties: id: type: string description: Unique identifier for this model. modelId: type: string description: Model identifier (for example "llama-3"). Error: type: object additionalProperties: false required: - statusCode - msg - details properties: errorCode: type: string description: Stable ngrok error code when available. statusCode: type: integer format: int32 description: HTTP status code for this error. msg: type: string description: Human-readable error message. details: type: object description: Structured error details. additionalProperties: type: string SupportedAPISurfaceParam: type: object additionalProperties: false required: - name properties: name: type: string description: Name of a supported top-level request body parameter. responses: Error: description: API error response. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer ````