openapi: 3.0.1
info:
  title: Nscale Serverless Inference Chat Models API
  description: OpenAI-compatible serverless inference API for Nscale. Provides chat completions, text completions, embeddings, image generation, and model discovery against open models (Llama, Qwen, DeepSeek, GPT OSS, Mistral, Flux) served on Nscale GPU infrastructure. Authenticate with a Bearer API key issued from the Nscale console.
  termsOfService: https://www.nscale.com/legal/terms-of-service
  contact:
    name: Nscale Support
    url: https://docs.nscale.com
  version: '1.0'
servers:
- url: https://inference.api.nscale.com/v1
  description: Serverless Inference API
security:
- bearerAuth: []
tags:
- name: Models
  description: Model catalog discovery.
paths:
  /models:
    get:
      operationId: listModels
      tags:
      - Models
      summary: List models
      description: Returns a list of serverless models available for inference, including identifiers and metadata such as context length and pricing.
      responses:
        '200':
          description: A list of available models.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /models/{model}:
    get:
      operationId: retrieveModel
      tags:
      - Models
      summary: Retrieve a model
      description: Returns metadata for a single model by identifier.
      parameters:
      - name: model
        in: path
        required: true
        description: The model identifier.
        schema:
          type: string
      responses:
        '200':
          description: The requested model.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Model'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          description: Model not found.
components:
  schemas:
    Model:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: model
        created:
          type: integer
        owned_by:
          type: string
        context_length:
          type: integer
        pricing:
          type: object
          description: Per-1M-token pricing metadata where exposed.
          additionalProperties: true
    ModelList:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string
  responses:
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Nscale API key issued from the console, sent as `Authorization: Bearer $NSCALE_API_KEY`.'