Cohere embed-multilingual-v3
Cohere's multilingual embedding model. Supports 100+ languages with separate search and classification modes.
Cohere embed-multilingual-v3 is embeddings AI model from Custom, priced at β¬0.100 per 1M input tokens with a 512 tokens context window.
Pricing
API Integration
Use our OpenAI-compatible API to integrate Cohere embed-multilingual-v3 into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
const vectors = await rw.run("cohere-embed-multilingual-v3", "Hello world", { type: "embed" });
console.log(vectors[0].length); // embedding dimensions
// Or use the embed() method for full control
const res = await rw.embed("cohere-embed-multilingual-v3", ["Hello", "World"]);
for (const item of res.data) {
console.log(item.embedding.length);
}Deep dive β Cohere's Cohere embed-multilingual-v3
Cohere was founded in 2019 in Toronto by Aidan Gomez (CEO), Nick Frosst and Ivan Zhang. Aidan Gomez is a co-author of the original Transformer paper 'Attention is All You Need' (2017) while at Google Brain; Nick Frosst is a former Geoffrey Hinton mentee. The company focuses on enterprise-grade large language models with a particular emphasis on retrieval, RAG, multilingual coverage and data sovereignty. Cohere has raised over $970M from investors including Inovia Capital, NVIDIA, Oracle, Salesforce Ventures, PSP Investments and the Canadian government's Strategic Innovation Fund, with a 2024 valuation of $5.5B. The Embed v3 family launched in November 2023 and remains one of the top-ranked commercial embedding models on the MTEB and BEIR retrieval leaderboards, especially for multilingual workloads.
Visit Cohere βCohere embed-multilingual-v3 is a bi-encoder Transformer that encodes text into a 1024-dimensional dense vector for retrieval. The model is the multilingual sibling of embed-english-v3 and supports more than 100 languages with cross-lingual semantic alignment, so that a German query can retrieve a relevant English document. Maximum input length is 512 tokens (~2,000 characters); longer documents must be chunked. The model was trained with a contrastive InfoNCE objective on a curated mix of multilingual question-answer pairs, web-search query-document pairs and licensed corpora, with deliberate down-weighting of low-quality web data. A signature feature is the input_type parameter, which lets the caller mark the input as 'search_document', 'search_query', 'classification' or 'clustering' to route through different projection heads tuned for each use case. The 1024-dim vectors are L2-normalised and accept cosine similarity directly. Cohere also offers a quantised int8 / binary endpoint for cheaper vector storage.
- Parameters
- Undisclosed
- Context
- 512 tokens
- 100+ languages with strong cross-lingual retrieval (DE query, EN doc)
- input_type parameter to specialise the embedding for query, document, classification or clustering
- 1024-dim L2-normalised vectors, cosine similarity
- int8 and binary quantisation endpoints for cheap vector storage
- Top-tier MTEB and BEIR retrieval scores for multilingual workloads
- Available on Cohere API, Amazon Bedrock, Oracle Cloud, Azure AI Studio
- Best for: multilingual RAG, cross-lingual search, enterprise knowledge bases
Contrastive training on a curated mix of multilingual QA pairs, search query-document pairs and licensed corpora. Exact token count not disclosed.
License: Proprietary commercial API. Available also on Amazon Bedrock and Oracle Cloud with separate licensing.
Known limitations
- Hard cap of 512 tokens per input
- 1024-dim vectors more expensive to store than 384-dim alternatives
- Closed weights; no on-premise deployment outside of Bedrock / Oracle
- Cross-lingual retrieval still weaker for very low-resource languages
- input_type parameter required for best quality
Frequently asked questions
Related Models
View all EmbeddingsBGE Large EN v1.5
BAAI (Beijing Academy of AI) open-weight English embedding model with 335M parameters. Returns 1024-dim vectors and was a top MTEB English retrieval model on release. The v1.5 update improved similarity distribution so it works well without a query instruction prefix for symmetric tasks. A widely used open alternative to hosted embeddings.
BGE-M3 (Multilingual)
BAAI multilingual embedding model covering 100+ languages with an 8192-token context. M3 stands for its multi-functionality (dense, sparse and ColBERT-style multi-vector retrieval), multilinguality and multi-granularity over long documents. Returns 1024-dim dense vectors and is a strong open choice for cross-lingual and long-text retrieval.
ESM-2 650M (Protein Embeddings)
Meta AI 650M-parameter protein language model trained on UniRef50 sequences. Feed it an amino-acid sequence and the per-residue hidden states act as learned protein embeddings, used for structure prediction, variant-effect and function tasks. This 33-layer checkpoint is the common balance of quality and cost in the ESM-2 family.
Nomic Embed Text v1.5
Nomic AI open embedding model with a fully reproducible training pipeline (open weights, data and code). Supports an 8192-token context and Matryoshka representation learning, so you can truncate the 768-dim output down to 64 dims with graceful quality loss. Uses task prefixes like search_query and search_document.
Start using Cohere embed-multilingual-v3 today
Get started with free credits. No credit card required. Access Cohere embed-multilingual-v3 and 100+ other models through a single API.