New case study: Delphi is using Pinecone to create over 100 million conversational agents with <30% of their total response time spent on retrieval. - Learn more
INFERENCE API

Request a Model

Looking to use a specific embedding model? What about a reranker? Request a model by filling out the form.

Pinecone Inference is an API service that gives you access to embedding models hosted on Pinecone’s infrastructure.