AI Models for Your GenAI Apps

Building GenAI applications with the right embedding and reranking models that suit your business.

Featured

How to Choose the Best Embedding Model for RAG in 2026: 10 Models Benchmarked

We benchmarked 10 embedding models on cross-modal, cross-lingual, long-document, and dimension compression tasks. See which one fits your RAG pipeline.

Read Now

Popular AI Models

Learn and compare top embedding and reranking models available in the market.

text-embedding-3-large
Embedding
Text
Proprietary
Milvus & Zilliz Cloud Integrated
OpenAI's best-performing text embedding model; Tailored for English text.
text-embedding-ada-002
Embedding
Text
Proprietary
Milvus Integrated
OpenAI's legacy text embedding model; with an average level of price and performance when compared with text-embedding-3-large and text-embedding-3-small.
text-embedding-3-small
Embedding
Text
Proprietary
Milvus & Zilliz Cloud Integrated
OpenAI's most cost-effective text embedding model with improved accuracy and efficiency compared to text-embedding-ada-002 and text-embedding-3-large.
jina-embeddings-v2-base-en
Embedding
Text
Apache 2.0
Milvus Integrated
Specialized embedding model for English text and long documents; support sequences of up to 8192 tokens
clip-vit-base-patch32
Embedding
Multimodal
Apache 2.0
Zilliz Cloud Integrated
A CLIP multimodal model variant that utilizes a ViT-B/32 Transformer architecture for image encoding and a masked self-attention Transformer for text encoding.
jina-embeddings-v2-small-en
Embedding
Text
Apache 2.0
Milvus Integrated
An English monolingual embedding model for a sequence length of up to 8192 tokens; the smallest variant in the Jina Embeddings v2 family.
voyage-code-2
Embedding
Text
Proprietary
Milvus Integrated
Voyage AI's text embedding model optimized for code retrieval (17% better than alternatives).
voyage-2
Embedding
Text
Proprietary
Milvus Integrated
Voyage AI's general-purpose text embedding model optimized for balancing cost, latency, and retrieval quality.
voyage-large-2
Embedding
Text
Proprietary
Milvus Integrated
Voyage AI’s general-purpose text embedding model; optimized for retrieval quality (e.g., better than OpenAI V3 Large); ideal for tasks like summarization, clustering, and classification.
embed-english-v3.0
Embedding
Text
Proprietary
Milvus Integrated
Tailored for English text; MTEB score: 64.5; BEIR score: 55.9
embed-english-light-v3.0
Embedding
Text
Proprietary
Milvus Integrated
A smaller, faster version of embed-english-v3.0. Almost as capable but a lot faster. English only.
embed-multilingual-v3.0
Embedding
Text
Proprietary
Milvus Integrated
Tailored for multilingual text; supports 100+ languages and can be used to search within a language and across languages; MTEB score: 64; BEIR score: 54.6
multilingual-e5-large
Embedding
Text
Mit
Milvus Integrated
Tailored for multilingual documents; supports 100+ languages; ideal for multilingual information retrieval and semantic search tasks.
e5-base-v2
Embedding
Text
Apache 2.0
Milvus Integrated
Ideal for good performance while keeping with open source and minimal hardware requirements. Works well on messy data. Good for short queries expected to return medium-length text passages (1-2 paragraphs).
e5-large-v2
Embedding
Text
Apache 2.0
Milvus Integrated
Ideal for good performance while keeping with open source and minimal hardware requirements. Works well on messy data. Good for short queries expected to return medium-length text passages (1-2 paragraphs).
mistral-embed
Embedding
Text
Proprietary
A specialized embedding model for text data with a context window of 8,000 tokens. Optimized for similarity retrieval and RAG applications. MTEB retrieval score: 55.26.
all-MiniLM-L12-v2
Embedding
Text
Apache 2.0
Milvus Integrated
A sentence and short paragraph encoder ideal for semantic search and RAG; based on the pre-trained Microsoft/MiniLM-L12-H384-uncased model and was fine-tuned on a large dataset of over 1 billion sentence pairs.
gte-large-en-v1.5
Embedding
Text
Apache 2.0
Milvus Integrated
Designed for embedding English text; Built upon the transformer++ encoder backbone (BERT + RoPE + GLU) and trained on a large-scale corpus of relevant text pairs.
gte-base-en-v1.5
Embedding
Text
Apache 2.0
Milvus Integrated
Specialized for English text; Built upon the transformer++ encoder backbone (BERT + RoPE + GLU)
instructor-large
Embedding
Text
Apache 2.0
An instruction-finetuned model tailored for text embeddings; better performance than `instructor-base`, but worse than `instructor-xl`.

AI Models for Your GenAI Apps

How to Choose the Best Embedding Model for RAG in 2026: 10 Models Benchmarked

Popular AI Models

text-embedding-3-large

text-embedding-ada-002

text-embedding-3-small

jina-embeddings-v2-base-en

clip-vit-base-patch32

jina-embeddings-v2-small-en

voyage-code-2

voyage-2

voyage-large-2

embed-english-v3.0

embed-english-light-v3.0

embed-multilingual-v3.0

multilingual-e5-large

e5-base-v2

e5-large-v2

mistral-embed

all-MiniLM-L12-v2

gte-large-en-v1.5

gte-base-en-v1.5

instructor-large

AI Assistant