Introduction
Overview
Welcome to the Mixedbread API Reference. This comprehensive guide provides detailed technical specifications for all our endpoints, including request/response schemas, code examples, and best practices.
Use our REST API directly or leverage our official Python & TypeScript SDKs for a more streamlined development experience.
New to Mixedbread? Start with our quickstart guide for a high-level overview of core concepts and use cases.
Base URL & Authentication
All API requests should be made to:
Include your API key in the Authorization header:
API Endpoints Overview
Our API is organized around five core endpoints, each designed for specific use cases:
Vector Stores
Create, manage, and search through your document collections with our AI native search engine.
Embeddings
Convert text into high-dimensional vectors for similarity search, clustering, and machine learning tasks.
Reranking
Improve search relevance by reordering results based on semantic similarity to your query.
Parsing
Extract LLM-ready content from PDFs and documents, including text, tables, and layout elements.
Files
Upload, manage, and retrieve files for use with parsing and vector store operations.
Quick Start Examples
Get up and running quickly with these common workflows:
Build a Search System
Upload documents, create a vector store, and implement semantic search in minutes.
Generate Embeddings
Convert text into vectors for similarity matching and AI applications.
Improve Search Results
Enhance existing search systems with semantic reranking capabilities.
Extract Document Data
Parse PDFs and extract structured content with layout preservation.
Last updated: June 5, 2025