Modelos de embeddings de texto
Classificações de modelos atualizadas com base em dados reais de uso.
Os modelos são classificados pelo total de tokens de prompt e de resposta processados pela API do OpenRouter nos últimos 7 dias. Exibindo os 10 melhores modelos. As classificações medem o uso no OpenRouter e refletem a adoção, não a qualidade do modelo ou o desempenho em testes de referência.
Modelos de embeddings convertem texto em vetores densos que permitem pesquisa semântica, geração aumentada por recuperação (RAG), agrupamento e correspondência por similaridade. Esta coleção classifica modelos de embeddings pelo uso no OpenRouter na última semana. Os melhores modelos atualmente são Qwen3 Embedding 8B, Text Embedding 3 Small e bge-m3. Acesse-os por meio de uma única API e compare dimensões, preços e desempenho sem gerenciar várias integrações com provedores.
Modelos de embeddings no OpenRouter
Qwen: Qwen3 Embedding 8B
226B tokens
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
OpenAI: Text Embedding 3 Small
170B tokens
text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
BAAI: bge-m3
41,8B tokens
The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.
Google: Gemini Embedding 001
32,9B tokens
gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March.
OpenAI: Text Embedding 3 Large
24,3B tokens
text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
Google: Gemini Embedding 2
18B tokens
Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.
Perplexity: Embed V1 0.6B
16,4B tokens
pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency embedding generation.
Qwen: Qwen3 Embedding 4B
10,4B tokens
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
VoyageAI by MongoDB: voyage-4
8,7B tokens
voyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embedd about voyage-4 here: mongodb.com/products/platform/ai-search-and-retrieval/models
Perplexity: Embed V1 4B
7,74B tokens
pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval quality.