Embedding

Compact Qwen3 embedding for edge and low-resource deployment. Apache 2.0.

Mid-size Qwen3 embedding balancing performance and efficiency. Apache 2.0.

#1 on MTEB multilingual leaderboard. Best open-source embedding model. Apache 2.0.

Most popular open-source multilingual embedding model. Supports dense, sparse, and multi-vector retrieval.

Cost-efficient embedding model balancing performance and price. 1536 dimensions.

Lightweight Voyage 4 variant for cost-sensitive workloads.

Previous generation Voyage model with strong retrieval performance.

Multilingual multimodal embedding model for 100+ languages. Leading multilingual retrieval benchmarks.

Top-performing embedding model using MoE architecture. Outperforms OpenAI and Cohere on retrieval benchmarks.

OpenAI's most capable embedding model. 3072 dimensions, strong across retrieval, classification, and clustering.

First natively multimodal embedding model supporting text, images, video, audio, and documents. 3072 dimensions, 100+ languages.

Multilingual text embedding model with Matryoshka representation learning.

Multimodal embedding model supporting text, images, and PDFs. Built on Qwen2.5-VL-3B with LoRA adapters.