Cohere Embed
Cohere's Embed is a leading multimodal embedding platform designed to transform text, images, or a combination of both into high-quality vector representations. These embeddings are optimized for semantic search, retrieval-augmented generation, classification, clustering, and agentic AI applications. The latest model, embed-v4.0, supports mixed-modality inputs, allowing users to combine text and images into a single embedding. It offers Matryoshka embeddings with configurable dimensions of 256, 512, 1024, or 1536, enabling flexibility in balancing performance and resource usage. With a context length of up to 128,000 tokens, embed-v4.0 is well-suited for processing large documents and complex data structures. It also supports compressed embedding types, including float, int8, uint8, binary, and ubinary, facilitating efficient storage and faster retrieval in vector databases. Multilingual support spans over 100 languages, making it a versatile tool for global applications.
Learn more
Gemini Embedding
Gemini Embedding’s first text model (gemini-embedding-001) is now generally available via the Gemini API and Gemini Enterprise Agent Platform, having held a top spot on the Massive Text Embedding Benchmark Multilingual leaderboard since its experimental launch in March, thanks to superior performance across retrieval, classification, and other embedding tasks compared to both legacy Google and external proprietary models. Exceptionally versatile, it supports over 100 languages with a 2,048‑token input limit and employs the Matryoshka Representation Learning (MRL) technique to let developers choose output dimensions of 3072, 153,6, or 768 for optimal quality, performance, and storage efficiency.
Learn more
EmbeddingGemma 2
EmbeddingGemma 2 is an open, lightweight multimodal embedding model designed to map text, code, images, video, and audio into a shared embedding space for search, retrieval, classification, routing, and RAG applications. Built on the Gemma 4 architecture and released under the Apache 2.0 license, it has 740 million parameters and is optimized for on-device inference. Its modular design can use as little as 270M parameters for text-only workloads, with optional vision and audio encoders for full multimodal support. Matryoshka Representation Learning lets developers reduce output vectors from 768 dimensions to 512, 256, or 128, lowering storage and memory requirements for local vector databases. The model supports an 8K-token context window and can process up to 5.5 minutes of audio, 29 images, 58 video frames, or interleaved combinations on local hardware.
Learn more
voyage-3-large
Voyage AI has unveiled voyage-3-large, a cutting-edge general-purpose and multilingual embedding model that leads across eight evaluated domains, including law, finance, and code, outperforming OpenAI-v3-large and Cohere-v3-English by averages of 9.74% and 20.71%, respectively. Enabled by Matryoshka learning and quantization-aware training, it supports embeddings of 2048, 1024, 512, and 256 dimensions, along with multiple quantization options such as 32-bit floating point, signed and unsigned 8-bit integer, and binary precision, significantly reducing vector database costs with minimal impact on retrieval quality. Notably, voyage-3-large offers a 32K-token context length, surpassing OpenAI's 8K and Cohere's 512 tokens. Evaluations across 100 datasets in diverse domains demonstrate its superior performance, with flexible precision and dimensionality options enabling substantial storage savings without compromising quality.
Learn more
