Pinecone

Pinecone Inference API

Use the Inference API to generate vector embeddings and rerank results using models hosted on Pinecone's infrastructure.

Documentation GitHub OpenAPI

Documentation

https://docs.pinecone.io/reference/api/introduction#inference-api

Specifications

https://raw.githubusercontent.com/api-evangelist/pinecone/refs/heads/main/openapi/pinecone-inference-openapi.yaml

OpenAPI Specification