AnnouncementPinecone serverless on AWS is now generally availableLearn more

Model Gallery

Need help picking the perfect model to enhance your Retrieval Augmented Generation (RAG) pipeline? Explore our curated gallery, showcasing a selection of the latest, most popular, and highly effective models.

Not seeing a model that fits your use case? !

Filters

text

text-embedding-3-large

Latest embedding model from OpenAI. Performance and cost optimization gains.

embedding

text

text-embedding-3-small

Latest embedding model from OpenAI. Performance and cost optimization gains.

embedding

text

rerank-english-v2.0

High performance text reranking model. Typically used as the second stage in two-stage retrieval pipelines.

reranker

text

e5-base-V2

Medium-sized open source text embedding model, offers great performance comparable to much larger models.

embedding

text

e5-large-V2

Good performance open source text embedding model.

embedding

text

all-MiniLM-L12-v2

Sentence-transformers model that maps sentences & paragraphs to vector space and can be used for tasks like clustering or semantic search.

embedding

multi-modal

CLIP

Open source multi-modal model from OpenAI trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image.

embedding

multi-modal

clip-ViT-B-32-multilingual-v1

multi-lingual version of the OpenAI CLIP-ViT-B32 model capable of encoding between text and image modalities.

embedding

text

multilingual-e5-large

Open source text embedding model, ideal for multilingual applications.

embedding

multi-modal

CLIP-ViT-B-32-laion2B-s34B-b79K

CLIP model trained on a massive dataset of text-image pairs to understand relationships between text and images.

embedding

text

Cohere-embed-english-v3.0

High performance text embedding model accessible via API.

embedding

text

Cohere-embed-multilingual-v3.0

High performance text embedding model accessible via API.

embedding

text

Cohere-embed-english-light-v3.0

Good performance text embedding model that outputs compressed vectors. Closed source model behind API.

embedding

text

mistral-embed

Designed with retrieval capabilities in mind. It achieves a retrieval score of 55.26 on MTEB.

embedding

text

voyage-large-2

Highest quality generalist text embedding model from second-generation of Voyage family. Includes a 16K context window.

embedding

text

voyage-code-2

Code embedding model from the second generation of the Voyage family. Includes a 16K context window.

embedding

text

voyage-02

Base text embedding model from second-generation of Voyage family. Mid-sized model optimized for latency and quality.

embedding

text

voyage-lite-02-instruct

Smallest text embedding model from second-generation of Voyage family. Optimized for latency and instruction-tuned for classification, clustering, and semantic similarity.

embedding

text

text-embedding-ada-002

Popular, good-performing text embedding model accessible via API.

embedding

text

all-mpnet-base-v2

Sentence-transformers model that maps sentences & paragraphs to vector space and can be used for tasks like clustering or semantic search.

embedding

text

jina-embeddings-v2-base-en

Strong text embedding model capable of embedding large text passages.

embedding

text

udever-bloom-7b1

Finetuned version of bigscience/bloom-7b1 that excels at multi-lingual text embeddings.

embedding

text

gte-large

Good performance open source text embedding model.

embedding

text

gte-base

Medium-sized open source text embedding model, offers great performance for the size.

embedding

text

instructor-base

Small text embedding model that can generate text embeddings tailored to any task or domain via natural language instructions.

embedding

text

instructor-large

Medium-size text embedding model that can generate text embeddings tailored to any task or domain via natural language instructions.

embedding

text

instructor-xl

Large text embedding model that can generate text embeddings tailored to any task or domain via natural language instructions.

embedding

text

voyage-01

Highest quality text embedding model from first-generation of Voyage family (for general purpose text embeddings).

embedding

text

voyage-lite-01

Fastest inference-time performance model for first-generation of Voyage family.

embedding

text

voyage-lite-01-instruct

Instruction-tuned model from first-generation of the Voyage family.

embedding