Featherless AI Embeddings API

openapi: 3.0.1
info:
  title: Featherless AI Chat Embeddings API
  description: OpenAI-compatible REST API for the Featherless AI serverless inference platform. A single Bearer-authenticated interface serves thousands of open-weight Hugging Face models for chat completions, legacy text completions, embeddings, and model discovery. Pricing is a flat monthly subscription with unlimited tokens rather than per-token billing.
  termsOfService: https://featherless.ai/terms
  contact:
    name: Featherless AI Support
    url: https://featherless.ai
  version: '1.0'
servers:
- url: https://api.featherless.ai/v1
  description: OpenAI-compatible base URL for Featherless AI inference.
security:
- bearerAuth: []
tags:
- name: Embeddings
  description: OpenAI-compatible text embeddings.
paths:
  /embeddings:
    post:
      operationId: createEmbedding
      tags:
      - Embeddings
      summary: Create embeddings
      description: Returns vector embeddings for the supplied input using an open embedding model (for example Qwen/Qwen3-Embedding-8B). OpenAI compatible.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateEmbeddingRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateEmbeddingResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
components:
  schemas:
    CreateEmbeddingRequest:
      type: object
      required:
      - model
      - input
      properties:
        model:
          type: string
          description: Embedding model identifier, e.g. `Qwen/Qwen3-Embedding-8B`.
        input:
          description: A string or array of strings to embed.
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        encoding_format:
          type: string
          enum:
          - float
          - base64
          default: float
        dimensions:
          type: integer
          nullable: true
          description: Output dimensionality, for models that support it.
    CreateEmbeddingResponse:
      type: object
      properties:
        object:
          type: string
          enum:
          - list
        model:
          type: string
        data:
          type: array
          items:
            type: object
            properties:
              object:
                type: string
                enum:
                - embedding
              index:
                type: integer
              embedding:
                type: array
                items:
                  type: number
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            total_tokens:
              type: integer
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string
              nullable: true
  responses:
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    TooManyRequests:
      description: Concurrency limit for the account's plan exceeded. Featherless meters concurrent connections rather than tokens.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: Featherless API key
      description: 'Set `Authorization: Bearer <FEATHERLESS_API_KEY>`. Keys are created in the Featherless dashboard.'