Mixedbread

Embeddings

Overview

Embeddings transform text into high-dimensional vectors that capture semantic meaning, enabling powerful similarity search, clustering, and machine learning applications.

Create Embeddings

POST/v1/embeddings

Converts text into dense vector representations. Supports both single strings and batch processing for efficiency.

Authorization

  • Authorization
    Authorization
    Type
    string
    Required or Optional
    required
    Bearer token for API authentication. Format: `Bearer YOUR_API_KEY`

Request Body

  • input
    input
    Type
    string|string[]
    Required or Optional
    required
    The text or list of texts to generate embeddings for.
    Constraints:
    Texts will be truncated if longer than the model's maximum sequence length
  • model
    model
    Type
    string
    Required or Optional
    required
    The identifier of the embedding model to use.
    Constraints:
    Must be a valid model. Refer to .
  • prompt
    prompt
    Type
    string
    Required or Optional
    optional
    An optional context prompt for the embedding model.
  • normalized
    normalized
    Type
    boolean
    Required or Optional
    optional
    Specifies whether output embeddings should be normalized to unit length.
  • dimensions
    dimensions
    Type
    number
    Required or Optional
    optional
    The desired dimensionality of the output embeddings for supported models.
  • encoding_format
    encoding_format
    Type
    string|string[]
    Required or Optional
    optional
    The desired encoding format for the output embeddings.
    Constraints:
    Options: float, float16, base64, binary, ubinary, int8, uint8

Response Body

  • model
    model
    Type
    string
    Required or Optional
    required
    The model identifier used for the request.
  • object
    object
    Type
    string
    Required or Optional
    required
    The type of the response object.
  • A list containing the generated embedding objects.
  • An object detailing the token usage for the request.
  • normalized
    normalized
    Type
    boolean
    Required or Optional
    required
    Indicates if the returned embeddings are normalized.
Vector Stores
API reference for managing and searching Mixedbread Vector Stores. This documentation covers all essential endpoints to work with vector stores and their associated files.
Files
API reference for managing files in Mixedbread. This documentation covers all essential endpoints to get you started with file management.

Last updated: June 11, 2025