openapi: 3.1.0 info: title: NVIDIA NIM Models API description: > OpenAI-compatible model catalog endpoint. Returns the list of models served by the NIM endpoint or self-hosted container — useful for discovering the exact `model` strings to pass to chat completions, completions, or embeddings. version: '2026-05-25' contact: name: NVIDIA Developer Support url: https://forums.developer.nvidia.com/c/ai-data-science/nemo-llm-service/ license: name: NVIDIA AI Enterprise License url: https://www.nvidia.com/en-us/data-center/products/ai-enterprise/ servers: - url: https://integrate.api.nvidia.com description: NVIDIA-hosted NIM endpoint - url: http://localhost:8000 description: Self-hosted NIM container default security: - BearerAuth: [] tags: - name: Models description: Model discovery operations paths: /v1/models: get: summary: List Available Models description: Return the list of models exposed by this NIM endpoint or container. operationId: listModels tags: - Models responses: '200': description: Model list. content: application/json: schema: $ref: '#/components/schemas/ModelList' '401': description: Missing or invalid API key. /v1/models/{model_id}: get: summary: Retrieve A Model description: Return metadata for a single model id. operationId: getModel tags: - Models parameters: - name: model_id in: path required: true schema: type: string responses: '200': description: Model object. content: application/json: schema: $ref: '#/components/schemas/Model' '404': description: Model not found. components: securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: nvapi-... schemas: ModelList: type: object properties: object: type: string example: list data: type: array items: $ref: '#/components/schemas/Model' Model: type: object properties: id: type: string example: meta/llama-3.3-70b-instruct object: type: string example: model created: type: integer owned_by: type: string example: meta root: type: string permission: type: array items: type: object