8 leading embedding models – including models that outperform OpenAI’s ada-002 and Cohere’s Embed-v3 in MTEB and LoCo Benchmarks.

Fully compatible with OpenAI API.

4x lower cost.

Integrated with MongoDB, LangChain, and LlamaIndex for RAG.

New "M2-Bert-Retrieval" models with up to 32k context length