テキスト埋め込みモデル

モデルランキングは に実際の利用データに基づいて更新されました。

モデルは、直近 7 日間に OpenRouter API を通じて処理されたプロンプトと補完の合計トークン数で順位付けされます。 上位 10 個のモデルを表示しています。 ランキングは OpenRouter での使用状況を測定し、モデルの品質やベンチマーク性能ではなく、採用状況を反映しています。

埋め込みモデルはテキストを密なベクトルに変換し、セマンティック検索、検索拡張生成(RAG)、クラスタリング、類似性マッチングを支えます。このコレクションでは、過去一週間の OpenRouter での使用状況に基づいて埋め込みモデルをランキングしています。 現在のトップモデルは Qwen3 Embedding 8B、Text Embedding 3 Small、Embed V1 0.6B です。 単一の API でアクセスし、複数のプロバイダーとの連携を管理することなく、次元数、料金、パフォーマンスを比較できます。

OpenRouter の埋め込みモデル

qwen のファビコン

Qwen: Qwen3 Embedding 8B

211B トークン

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.

作成者: qwen$0.01/M 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.

作成者: openai$0.02/M tokens
perplexity のファビコン

Perplexity: Embed V1 0.6B

88.9B トークン

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.

作成者: perplexity$0.004/M tokens
baai のファビコン

BAAI: bge-m3

45.6B トークン

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.

作成者: baai$0.01/M 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.

作成者: openai$0.13/M tokens
qwen のファビコン

Qwen: Qwen3 Embedding 4B

26.9B トークン

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.

作成者: qwen$0.02/M tokens
google のファビコン

Google: Gemini Embedding 2

18.8B トークン

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.

作成者: google$0.20/M tokens

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

作成者: mongodb$0.12/M tokens
google のファビコン

Google: Gemini Embedding 001

11.8B トークン

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.

作成者: google$0.15/M tokens

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

作成者: mongodb$0.02/M tokens

その他のコレクションを見る