FriendliAI Serverless.Model API

openapi: 3.1.0
info:
  title: Friendli Suite API Reference Container.Audio Serverless.Model API
  description: This is an OpenAPI reference of Friendli Suite API.
  termsOfService: https://friendli.ai/terms-of-service
  contact:
    name: FriendliAI Support Team
    email: support@friendli.ai
  version: 0.1.0
servers:
- url: https://api.friendli.ai
tags:
- name: Serverless.Model
paths:
  /serverless/v1/models:
    get:
      tags:
      - Serverless.Model
      summary: Retrieve serverless models
      description: Retrieve list of serverless models.
      operationId: serverlessModelList
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerlessModelListSuccess'
        '400':
          description: Bad Request
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: list
      x-speakeasy-ignore: true
  /serverless/v1/openrouter/models:
    get:
      tags:
      - Serverless.Model
      summary: Retrieve serverless models for OpenRouter
      description: Retrieve list of serverless models for OpenRouter integration.
      operationId: serverlessOpenrouterModelList
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenRouterModelListSuccess'
        '400':
          description: Bad Request
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: listOpenrouter
      x-speakeasy-ignore: true
components:
  schemas:
    OpenRouterModelMetadata:
      properties:
        slug:
          type: string
          title: Slug
          description: OpenRouter model slug
      type: object
      required:
      - slug
      title: OpenRouterModelMetadata
      description: OpenRouter model metadata.
    OpenRouterModelListSuccess:
      properties:
        data:
          items:
            $ref: '#/components/schemas/OpenRouterModelCatalogResponseItem'
          type: array
          title: Data
      type: object
      required:
      - data
      title: OpenRouterModelListSuccess
      description: '`/v1/openrouter/models` API response.'
    OpenRouterModelCatalogResponseItem:
      properties:
        id:
          type: string
          title: Id
        hugging_face_id:
          type: string
          title: Hugging Face Id
          description: Required when the model is hosted on Hugging Face
          default: ''
        name:
          type: string
          title: Name
        created:
          type: integer
          title: Created
        input_modalities:
          items:
            type: string
          type: array
          title: Input Modalities
        output_modalities:
          items:
            type: string
          type: array
          title: Output Modalities
        quantization:
          anyOf:
          - type: string
          - type: 'null'
          title: Quantization
          description: Model quantization level
        context_length:
          type: integer
          title: Context Length
        max_output_length:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Output Length
        pricing:
          anyOf:
          - $ref: '#/components/schemas/OpenRouterPricingTier'
          - items:
              $ref: '#/components/schemas/OpenRouterPricingTier'
            type: array
          title: Pricing
          description: Token prices in USD per token as strings
        supported_sampling_parameters:
          items:
            type: string
          type: array
          title: Supported Sampling Parameters
        supported_features:
          items:
            type: string
          type: array
          title: Supported Features
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
        deprecation_date:
          anyOf:
          - type: string
          - type: 'null'
          title: Deprecation Date
          description: ISO 8601 UTC hour (YYYY-MM-DDTHH:00:00Z)
        is_ready:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Is Ready
          description: Whether the model is ready to serve traffic on OpenRouter
        is_free:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Is Free
          description: Whether the model is offered as a free endpoint
        discount_to_user:
          anyOf:
          - type: number
          - type: 'null'
          title: Discount To User
          description: Fractional discount applied to user-facing pricing
        capacity_tpm:
          anyOf:
          - type: integer
          - type: 'null'
          title: Capacity Tpm
          description: Input tokens per minute capacity
        openrouter:
          anyOf:
          - $ref: '#/components/schemas/OpenRouterModelMetadata'
          - type: 'null'
          title: Openrouter
        datacenters:
          anyOf:
          - items:
              $ref: '#/components/schemas/OpenRouterDatacenter'
            type: array
          - type: 'null'
          title: Datacenters
      type: object
      required:
      - id
      - name
      - created
      - input_modalities
      - output_modalities
      - context_length
      - pricing
      - supported_sampling_parameters
      - supported_features
      title: OpenRouterModelCatalogResponseItem
      description: Model listing in `/v1/openrouter/models` API (OpenRouter provider format).
    ModelCatalogResponseItem:
      properties:
        id:
          type: string
          title: Id
        hugging_face_id:
          type: string
          title: Hugging Face Id
          description: Required when the model is hosted on Hugging Face
          default: ''
        name:
          type: string
          title: Name
        created:
          type: integer
          title: Created
        context_length:
          type: integer
          title: Context Length
        max_completion_tokens:
          type: integer
          title: Max Completion Tokens
        pricing:
          $ref: '#/components/schemas/PricingModel'
          title: Pricing
          description: Token prices for input and output
        functionality:
          $ref: '#/components/schemas/Functionality'
          description: Model functionality
        description:
          type: string
          title: Description
        deprecation_date:
          anyOf:
          - type: string
          - type: 'null'
          title: Deprecation Date
          description: ISO 8601 UTC hour (YYYY-MM-DDTHH:00:00Z)
        hugging_face_url:
          type: string
          minLength: 1
          format: uri
          title: Hugging Face Url
        license:
          type: string
          minLength: 1
          format: uri
          title: License
        discount_to_user:
          anyOf:
          - type: number
          - type: 'null'
          title: Discount To User
          description: Fractional discount applied to user-facing pricing
      type: object
      required:
      - id
      - name
      - created
      - context_length
      - max_completion_tokens
      - pricing
      - functionality
      - description
      - hugging_face_url
      - license
      title: ModelCatalogResponseItem
      description: Model listing in `/v1/models` API.
    OpenRouterPricingTier:
      properties:
        prompt:
          type: string
          title: Prompt
          description: Price per input token in USD
        completion:
          type: string
          title: Completion
          description: Price per output token in USD
        image:
          type: string
          title: Image
          description: Price per image in USD (base tier only)
          default: '0'
        request:
          type: string
          title: Request
          description: Price per request in USD (base tier only)
          default: '0'
        input_cache_read:
          anyOf:
          - type: string
          - type: 'null'
          title: Input Cache Read
          description: Price per cached input token read in USD
        min_context:
          anyOf:
          - type: integer
          - type: 'null'
          title: Min Context
          description: Minimum input tokens for this tier to apply
      type: object
      required:
      - prompt
      - completion
      title: OpenRouterPricingTier
      description: OpenRouter flat or tiered pricing entry (USD per unit as string).
    OpenRouterDatacenter:
      properties:
        country_code:
          type: string
          title: Country Code
          description: ISO 3166-1 alpha-2 country code
      type: object
      required:
      - country_code
      title: OpenRouterDatacenter
      description: OpenRouter datacenter metadata.
    ServerlessModelListSuccess:
      properties:
        data:
          items:
            $ref: '#/components/schemas/ModelCatalogResponseItem'
          type: array
          title: Data
      type: object
      required:
      - data
      title: ServerlessModelListSuccess
      description: '`/v1/models` API response.'
    Functionality:
      properties:
        tool_call:
          type: boolean
          title: Tool Call
        builtin_tool:
          type: boolean
          title: Built-in Tool
        parallel_tool_call:
          type: boolean
          title: Tool Call Parallel
        structured_output:
          type: boolean
          title: Structured Output
          default: true
      type: object
      required:
      - tool_call
      - builtin_tool
      - parallel_tool_call
      title: Functionality
      description: Functionality of the model.
    PricingModel:
      properties:
        input:
          type: string
          title: Input
          description: Price per input token in USD
        output:
          type: string
          title: Output
          description: Price per output token in USD
        prompt:
          type: string
          title: Prompt
          description: Price per input token in USD (alias of input)
        completion:
          type: string
          title: Completion
          description: Price per output token in USD (alias of output)
        input_cache_read:
          anyOf:
          - type: string
          - type: 'null'
          title: Input Cache Read
          description: Price per cached input token read in USD
        audio_minute:
          anyOf:
          - type: string
          - type: 'null'
          title: Audio Minute
          description: Price per audio minute in USD
      type: object
      required:
      - input
      - output
      - prompt
      - completion
      title: PricingModel
      description: Pricing model for token-based pricing.
  securitySchemes:
    token:
      type: http
      description: 'When using Friendli Suite API for inference requests, you need to provide a **Friendli Token** for authentication and authorization purposes.


        For more detailed information, please refer [here](https://friendli.ai/docs/openapi/introduction#authentication).'
      scheme: bearer
x-speakeasy-retries:
  strategy: backoff
  backoff:
    initialInterval: 500
    maxInterval: 60000
    maxElapsedTime: 3600000
    exponent: 1.5
  statusCodes:
  - 429
  - 500
  - 502
  - 503
  - 504
  retryConnectionErrors: true