Turn text into vector Embeddings & RAG for semantic search, recommendation, and retrieval-augmented generation — through one simple API call.
6 models live
768–4096 dimensions
Model description
Execute job request via HTTP POST
Check the status of a job execution
Run asynchronous job and poll for result in Python
From conversational products to backend reasoning pipelines — one API surface for every text workload.
Search over documents, products, or support content by meaning, not just keyword overlap.
Retrieve the right context and feed it into an LLM for grounded, up-to-date generation.
Similarity-matching features that surface related items, content, or users at scale.
