{"slug":"voyage-3-large","name":"Voyage 3 Large","domain":null,"best_rank":4,"categories":1,"entries":[{"slug":"best-multilingual-embedding-api-for-semantic-search","title":"Best multilingual embedding API for semantic search","rank":4,"of":13,"score":7,"appearances":2,"modelRanks":{"Claude":3,"Gemini":2},"reason":"Leader in raw retrieval accuracy for specialized domains (finance, law, code) across 300+ languages (nearly tied with Cohere Embed v4 on general text retrieval), featuring a 32k context window and native support for low-bit quantization (int8/binary) to drastically reduce database costs.","reasons":[{"model":"Gemini","reason":"Leader in raw retrieval accuracy for specialized domains (finance, law, code) across 300+ languages (nearly tied with Cohere Embed v4 on general text retrieval), featuring a 32k context window and native support for low-bit quantization (int8/binary) to drastically reduce database costs."},{"model":"Claude","reason":"Best-in-class retrieval accuracy per dollar in head-to-head RAG evaluations, strong multilingual coverage despite less marketing around it, 32K context, and quantization-aware Matryoshka embeddings that keep storage tiny; the Anthropic-recommended-turned-MongoDB-acquired lineage has kept the API stable and retrieval-focused."}],"fixes":[{"model":"Claude","fix":"Multilingual breadth is thinner than Cohere/Google in low-resource languages, and the model lineup churns fast enough that re-embedding to stay current is a recurring tax."},{"model":"Gemini","fix":"Proprietary API with no self-hosted or open-weight options, binding users to Voyage AI's hosted infrastructure and partner platforms."}],"updated":"2026-07-17","api":"https://modelsagree.com/api/v1/best/best-multilingual-embedding-api-for-semantic-search.json"}],"page":"https://modelsagree.com/product/voyage-3-large","check":"https://modelsagree.com/check?q=Voyage%203%20Large","updated":"2026-07-17T17:56:55.557Z","attribution":"modelsagree.com, CC BY 4.0"}