Fast Text Embeddings API

Production-ready embedding service powered by state-of-the-art BERT models. Generate high-quality vector representations for semantic search, RAG, and more.

⚡ Fast

Optimized ONNX runtime with intelligent caching for blazing-fast embeddings

🔒 Secure

API key authentication with rate limiting and usage tracking

📊 Scalable

Built with Rust for high performance and reliable production deployments