> ## Documentation Index > Fetch the complete documentation index at: https://docs.slng.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update a client model > Update one client model owned by your organisation. Send the fields you want to change (at least one is required); omitted fields keep their stored values. A model owned by another organisation returns 404. The write-only `api_key`, `vertex_credentials`, and `aws_credentials` fields overwrite the stored secret when supplied and are never returned. ## OpenAPI ````yaml api-reference/agents/client-models.oas.yaml PUT /v1/agents/client-models/{client_model_id} openapi: 3.1.0 info: title: SLNG Agent Resources — Client models version: 1.0.0 description: >- Public API for organisation tools, MCP servers, Vault entries, and BYOK client models. contact: name: SLNG Support email: support@slng.ai servers: - url: https://api.agents.slng.ai description: Production security: - bearerAuth: [] paths: /v1/agents/client-models/{client_model_id}: put: summary: Update Client Model description: >- Update one client model owned by your organisation. Send the fields you want to change (at least one is required); omitted fields keep their stored values. A model owned by another organisation returns 404. The write-only `api_key`, `vertex_credentials`, and `aws_credentials` fields overwrite the stored secret when supplied and are never returned. operationId: updateClientModel parameters: - name: client_model_id in: path required: true description: >- The UUID of the client model to update. A model owned by another organisation returns 404. example: 6a3f5b2c-1d4e-4f8a-9b0c-2e3d4f5a6b7c schema: type: string format: uuid title: Client Model Id requestBody: required: true description: >- The fields to change on the client model. At least one must be supplied. content: application/json: schema: $ref: '#/components/schemas/ClientModelUpdate' examples: Rotate API key: summary: Rotate the stored upstream API key value: api_key: sk-proj-new-example Rename model: summary: Point the alias at a different upstream model value: model_name: gpt-4o responses: '200': description: The updated client model. content: application/json: schema: $ref: '#/components/schemas/ClientModelOut' '401': $ref: '#/components/responses/UnauthorizedError' '403': $ref: '#/components/responses/ForbiddenError' '404': $ref: '#/components/responses/NotFoundError' '409': $ref: '#/components/responses/ConflictError' '422': $ref: '#/components/responses/ValidationError' '429': $ref: '#/components/responses/RateLimitError' '500': $ref: '#/components/responses/InternalServerError' components: schemas: ClientModelUpdate: properties: url: anyOf: - type: string maxLength: 2000 minLength: 1 - type: 'null' title: Url api_key: anyOf: - type: string minLength: 1 - type: 'null' description: >- A replacement upstream provider API key. Write-only: overwrites the stored key and is never returned. Required for openai-compat, openai-responses, and azure; rejected for vertex. title: Api Key writeOnly: true model_name: anyOf: - type: string maxLength: 255 minLength: 1 - type: 'null' description: >- A new alias for the model. Sent upstream as-is unless `model_id` is set. title: Model Name model_id: anyOf: - type: string maxLength: 255 - type: 'null' description: >- A new upstream provider-facing model id. Empty or null sends `model_name` as-is. title: Model Id provider: anyOf: - type: string enum: - openai-compat - openai-responses - azure - vertex - type: 'null' description: >- The bring-your-own model provider to set. Changing it re-checks the per-provider field requirements against the merged record. Values: `openai-compat` and `openai-responses` (OpenAI-compatible endpoints), `azure` (Azure OpenAI), and `vertex` (Google Vertex AI). title: Provider model_lab: anyOf: - type: string maxLength: 100 - type: 'null' title: Model Lab azure_deployment: anyOf: - type: string maxLength: 255 - type: 'null' description: A new Azure OpenAI deployment name. Azure only. title: Azure Deployment api_version: anyOf: - type: string maxLength: 100 - type: 'null' description: A new Azure OpenAI API version. Azure only. title: Api Version auth_header: anyOf: - type: string maxLength: 64 - type: 'null' description: >- openai-compat and openai-responses only: change the custom credential header name that replaces the default Authorization Bearer scheme. Rejected for azure and vertex. title: Auth Header vertex_credentials: anyOf: - type: object additionalProperties: true - type: 'null' description: >- Vertex only: a replacement GCP service-account key JSON. Write-only; stored encrypted and never returned (responses expose `has_vertex_credentials`). title: Vertex Credentials writeOnly: true vertex_location: anyOf: - type: string maxLength: 100 - type: 'null' title: Vertex Location vertex_project: anyOf: - type: string maxLength: 100 - type: 'null' title: Vertex Project aws_credentials: anyOf: - type: object additionalProperties: true - type: 'null' description: >- Speech BYOK only: replacement AWS SigV4 credentials (access_key_id, secret_access_key, region). Write-only; stored encrypted and never returned (responses expose `has_aws_credentials`). title: Aws Credentials writeOnly: true languages: anyOf: - items: type: string type: array - type: 'null' title: Languages regions: anyOf: - items: type: string type: array - type: 'null' title: Regions enabled: anyOf: - type: boolean - type: 'null' title: Enabled kwargs: anyOf: - type: object additionalProperties: true - type: 'null' title: Kwargs fallbacks: anyOf: - items: $ref: '#/components/schemas/LlmRouterConfigEntry' type: array maxItems: 2 - type: 'null' title: Fallbacks type: object title: ClientModelUpdate description: >- Fields to change on an existing client model. All are optional and at least one must be supplied; omitted fields keep their stored values. Write-only credential fields overwrite the stored secret when provided. example: model_name: gpt-4o enabled: false ClientModelOut: properties: id: type: string format: uuid title: Id org_id: type: string format: uuid title: Org Id api_key_id: anyOf: - type: string format: uuid - type: 'null' description: >- Speech BYOK only: the API key id this credential is scoped to, or null for the organisation default. Non-secret. title: Api Key Id service_type: type: string enum: - llm - stt - tts description: 'The kind of model: `llm`, `stt`, or `tts`.' title: Service Type provider: anyOf: - type: string - type: 'null' description: >- The configured provider. May be a legacy free-form label on records created before the current provider set. title: Provider model_lab: anyOf: - type: string - type: 'null' title: Model Lab url: anyOf: - type: string - type: 'null' title: Url has_api_key: type: boolean description: >- Whether an upstream API key is stored. The key value is write-only and never returned. title: Has Api Key auth_header: anyOf: - type: string - type: 'null' description: >- The custom credential header name, or null for the default Authorization Bearer scheme. The credential value itself is never returned. title: Auth Header model_name: type: string description: The configured alias for the model. title: Model Name model_id: anyOf: - type: string - type: 'null' description: >- The upstream provider-facing model id, or null when `model_name` is sent as-is. title: Model Id fallbacks: anyOf: - items: $ref: '#/components/schemas/LlmRouterConfigEntry' type: array - type: 'null' title: Fallbacks azure_deployment: anyOf: - type: string - type: 'null' description: The configured Azure OpenAI deployment name (Azure only). title: Azure Deployment api_version: anyOf: - type: string - type: 'null' description: The configured Azure OpenAI API version (Azure only). title: Api Version has_vertex_credentials: type: boolean description: >- Whether Vertex service-account credentials are stored. The value is write-only and never returned. title: Has Vertex Credentials has_aws_credentials: type: boolean description: >- Whether AWS SigV4 credentials are stored. The value is write-only and never returned. title: Has Aws Credentials vertex_location: anyOf: - type: string - type: 'null' title: Vertex Location vertex_project: anyOf: - type: string - type: 'null' title: Vertex Project languages: items: type: string type: array title: Languages regions: anyOf: - items: type: string type: array - type: 'null' title: Regions enabled: type: boolean title: Enabled kwargs: anyOf: - type: object additionalProperties: true - type: 'null' title: Kwargs created_at: type: string format: date-time title: Created At updated_at: type: string format: date-time title: Updated At type: object required: - id - org_id - service_type - provider - model_lab - url - has_api_key - auth_header - model_name - model_id - azure_deployment - api_version - has_vertex_credentials - has_aws_credentials - vertex_location - vertex_project - languages - regions - enabled - kwargs - created_at - updated_at title: ClientModelOut description: >- A client model as returned by the API. Credential values are never included; `has_api_key`, `has_vertex_credentials`, and `has_aws_credentials` report whether each secret is stored, and `fallbacks` lists the configured fallback cascade. example: id: 6a3f5b2c-1d4e-4f8a-9b0c-2e3d4f5a6b7c org_id: 1b2c3d4e-5f6a-7b8c-9d0e-1f2a3b4c5d6e api_key_id: null service_type: llm provider: openai-compat model_lab: null url: https://api.openai.com/v1 has_api_key: true auth_header: null model_name: gpt-4o-mini model_id: null fallbacks: [] azure_deployment: null api_version: null has_vertex_credentials: false has_aws_credentials: false vertex_location: null vertex_project: null languages: [] regions: null enabled: true kwargs: null created_at: '2026-01-15T09:30:00Z' updated_at: '2026-01-15T09:30:00Z' LlmRouterConfigEntry: properties: client_model_id: anyOf: - type: string format: uuid - type: 'null' description: >- Bring-your-own model reference: the id of one of your client models. Mutually exclusive with `catalog_model_code` (set at most one). title: Client Model Id catalog_model_code: anyOf: - type: string maxLength: 255 minLength: 1 - type: 'null' description: >- SLNG-managed model reference: a catalog model code. Mutually exclusive with `client_model_id`. title: Catalog Model Code type: object title: LlmRouterConfigEntry description: >- One slot in a config's ordered fallback cascade (``entries``). Exactly one of ``client_model_id`` (BYOK) or ``catalog_model_code`` (Slng-managed) — the same XOR as the row-level model reference. Org ownership / catalog entitlement are checked in the service layer (needs the DB session); position in the list is the tier the sync derives (1-based). example: client_model_id: 6a3f5b2c-1d4e-4f8a-9b0c-2e3d4f5a6b7c catalog_model_code: null ApiErrorResponse: type: object description: >- Error envelope returned by failed requests. `detail` is a short message and `error` carries the structured code and metadata. required: - detail - error properties: detail: type: string error: $ref: '#/components/schemas/ApiErrorDetail' example: detail: client model not found error: code: NOT_FOUND message: client model not found request_id: req_01H8XYZ retryable: false ApiErrorDetail: type: object description: >- Structured error body: a stable machine-readable `code`, a human-readable `message`, and optional `request_id`, `retryable`, and per-field validation details. required: - code - message properties: code: type: string description: Stable machine-readable error code. example: NOT_FOUND message: type: string example: client model not found request_id: type: - string - 'null' example: req_01H8XYZ retryable: type: boolean example: false fields: type: array items: type: object additionalProperties: true example: [] example: code: NOT_FOUND message: client model not found request_id: req_01H8XYZ retryable: false responses: UnauthorizedError: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' ForbiddenError: description: >- The caller cannot perform this operation, or public resource access is disabled for the organisation. Disabled access returns code PUBLIC_SHARED_RESOURCES_DISABLED with retryable set to false. content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' NotFoundError: description: Resource not found. content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' ConflictError: description: The requested change conflicts with the current resource state. content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' ValidationError: description: Request validation failed. content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' RateLimitError: description: The organisation's request limit was exceeded. headers: Retry-After: schema: type: integer X-RateLimit-Limit: schema: type: integer X-RateLimit-Remaining: schema: type: integer content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' InternalServerError: description: The operation failed. The response does not expose secret values. content: application/json: schema: $ref: '#/components/schemas/ApiErrorResponse' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: SLNG API key description: Your SLNG consumer API key. ````