Model Gallery - Pinecone Docs

Inference

Build end-to-end faster with models hosted by Pinecone.

llama-text-embed-v2

NVIDIA

State of the art text embedding model

TaskEmbedding

ModalityText

Max Input Tokens2048

Price$0.16 / million tokens

MICROSOFT

Top performing text embedding model from Microsoft research.

TaskEmbedding

ModalityText

Max Input Tokens507

Price$0.08 / million tokens

COHERE

Cohere's latest reranker with multilingual capabilities.

TaskRerank

ModalityText

Max Input Tokens4096

Price$2.00 / 1k requests

PINECONE

Sparse vector model for keyword-style search.

TaskEmbedding

ModalityText

Max Input Tokens512

Price$0.08 / million tokens

BAAI

High performance multi-lingual reranker model.

TaskRerank

ModalityText

Max Input Tokens1024

Price$2.00 / 1k requests