> ## Documentation Index > Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details. # Create or update a model provider > Create or update a model provider ## OpenAPI ````yaml PUT /api/v1/model-providers/{provider} openapi: 3.1.0 info: title: LangWatch API description: LangWatch openapi spec version: 1.0.0 servers: - url: https://app.langwatch.ai security: - project_api_key: [] paths: /api/v1/model-providers/{provider}: put: tags: - Model Providers description: Create or update a model provider operationId: putApiModelProvidersByProvider parameters: - in: path name: provider schema: type: string minLength: 1 required: true requestBody: required: true content: application/json: schema: type: object properties: enabled: type: boolean customKeys: type: object propertyNames: type: string additionalProperties: {} customModels: anyOf: - type: array items: type: object properties: modelId: type: string minLength: 1 displayName: type: string minLength: 1 mode: type: string enum: - chat - embedding maxTokens: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' supportedParameters: type: array items: type: string enum: - temperature - max_tokens - top_p - frequency_penalty - presence_penalty - top_k - min_p - repetition_penalty - seed - reasoning - verbosity multimodalInputs: type: array items: type: string enum: - image - file - audio required: - modelId - displayName - mode additionalProperties: false - type: array items: type: string customEmbeddingsModels: anyOf: - type: array items: type: object properties: modelId: type: string minLength: 1 displayName: type: string minLength: 1 mode: type: string enum: - chat - embedding maxTokens: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' supportedParameters: type: array items: type: string enum: - temperature - max_tokens - top_p - frequency_penalty - presence_penalty - top_k - min_p - repetition_penalty - seed - reasoning - verbosity multimodalInputs: type: array items: type: string enum: - image - file - audio required: - modelId - displayName - mode additionalProperties: false - type: array items: type: string extraHeaders: type: array items: type: object properties: key: type: string value: type: string required: - key - value defaultModel: type: string required: - enabled responses: '200': description: Success content: application/json: schema: type: object properties: {} additionalProperties: type: object properties: id: type: string provider: type: string enabled: type: boolean customKeys: anyOf: - type: object propertyNames: type: string additionalProperties: {} - type: 'null' deploymentMapping: anyOf: - {} - type: 'null' models: anyOf: - type: array items: type: string - type: 'null' embeddingsModels: anyOf: - type: array items: type: string - type: 'null' customModels: anyOf: - type: array items: type: object properties: modelId: type: string minLength: 1 displayName: type: string minLength: 1 mode: type: string enum: - chat - embedding maxTokens: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' supportedParameters: type: array items: type: string enum: - temperature - max_tokens - top_p - frequency_penalty - presence_penalty - top_k - min_p - repetition_penalty - seed - reasoning - verbosity multimodalInputs: type: array items: type: string enum: - image - file - audio required: - modelId - displayName - mode additionalProperties: false - type: 'null' customEmbeddingsModels: anyOf: - type: array items: type: object properties: modelId: type: string minLength: 1 displayName: type: string minLength: 1 mode: type: string enum: - chat - embedding maxTokens: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' supportedParameters: type: array items: type: string enum: - temperature - max_tokens - top_p - frequency_penalty - presence_penalty - top_k - min_p - repetition_penalty - seed - reasoning - verbosity multimodalInputs: type: array items: type: string enum: - image - file - audio required: - modelId - displayName - mode additionalProperties: false - type: 'null' disabledByDefault: type: boolean extraHeaders: anyOf: - type: array items: type: object properties: key: type: string value: type: string required: - key - value additionalProperties: false - type: 'null' required: - provider - enabled - customKeys - deploymentMapping additionalProperties: false '400': description: Bad Request content: application/json: schema: type: object properties: error: type: string message: type: string required: - error '401': description: Unauthorized content: application/json: schema: type: object properties: error: type: string message: type: string required: - error '409': description: Conflict content: application/json: schema: type: object properties: error: type: string message: type: string required: - error - message '422': description: Unprocessable Entity content: application/json: schema: type: object properties: error: type: string message: type: string required: - error '500': description: Internal Server Error content: application/json: schema: type: object properties: error: type: string message: type: string required: - error security: - project_api_key: [] components: securitySchemes: project_api_key: type: apiKey in: header name: X-Auth-Token description: >- Project API key for sending traces and accessing project-scoped resources. Format: sk-lw-... (no underscore). Obtain one by creating a project via the Admin API or the LangWatch UI. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.