Text Embedding Models
Model rankings updated based on real usage data.
Models are ranked by total prompt and completion tokens processed through the OpenRouter API over the trailing 7 days. Showing the top 10 models. Rankings measure usage on OpenRouter and reflect adoption, not model quality or benchmark performance.
Embedding models convert text into dense vectors that power semantic search, retrieval-augmented generation (RAG), clustering, and similarity matching. This collection ranks embedding models by their usage on OpenRouter over the past week. The current top models are Qwen3 Embedding 8B, Text Embedding 3 Small, and bge-m3. Access them through one API and compare dimensions, pricing, and performance without managing multiple provider integrations.
Embedding Models on OpenRouter

Qwen: Qwen3 Embedding 8B
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
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
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.

Qwen: Qwen3 Embedding 4B
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 Large
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
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
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.
Google: Gemini Embedding 001
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.

VoyageAI by MongoDB: voyage-4-lite
voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings t voyage-4-lite here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: voyage-4-large
voyage-4-large is a state-of-the-art general-purpose and multilingual embedding optimized for retrieval quality. Enabled by Matryoshka learning and quantization-aware training, voyage-4-large supports embeddings voyage-4-large here: mongodb.com/products/platform/ai-search-and-retrieval/models
Frequently asked questions
Send POST /api/v1/embeddings with a model slug from this page and your text in input. Pass an array of strings to batch multiple texts in one request. The response returns vectors in data[].embedding — see the Embeddings API reference for request options such as encoding_format.
Call GET /api/v1/embeddings/models to retrieve the full catalog of embedding models on OpenRouter, including pricing and context limits.
Embedding models are billed per input token, and each listing above shows its per-token price. Batching multiple strings in one input array reduces request overhead while paying the same per-token rate.
Yes. Use an embedding model from this page for initial vector retrieval, then refine the top candidates with a model from the rerank models collection.
No. One OpenRouter API key works for every embedding model and every chat or multimodal model on OpenRouter. Create a key on your API keys page.