Jina Embeddings v3 (Multilingual)
Jina's frontier multilingual embedding model. 570M params, 8192 ctx, 89 languages, Matryoshka dims 128-1024.
Jina Embeddings v3 (Multilingual) is embeddings AI model from Custom, priced at €0.020 per 1M input tokens with a 8.2K tokens context window.
Pricing
API Integration
Use our OpenAI-compatible API to integrate Jina Embeddings v3 (Multilingual) into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
const vectors = await rw.run("jina-embeddings-v3-multilingual", "Hello world", { type: "embed" });
console.log(vectors[0].length); // embedding dimensions
// Or use the embed() method for full control
const res = await rw.embed("jina-embeddings-v3-multilingual", ["Hello", "World"]);
for (const item of res.data) {
console.log(item.embedding.length);
}Deep dive — Jina AI's Jina Embeddings v3 (Multilingual)
Jina AI was founded in February 2020 in Berlin by Han Xiao (CEO, ex-Tencent and Zalando) together with co-founders Maximilian Werk, Christina Reher and Vincent Zhang. The company started as an open-source neural search framework (Jina, DocArray) and later pivoted to building proprietary multimodal embedding and reranking models offered through a hosted API. Jina has raised over $40M from investors including Canaan Partners, Mango Capital, Yunqi Partners and SAP, and ships its products under a freemium model. The Jina Embeddings v3 family was released in September 2024 and was the first open-weights embedding model to feature task-specific Low-Rank Adaptation (LoRA) heads selected at inference time, plus an 8,192-token context window. The release was widely covered as a top-tier multilingual embedding alternative on the MTEB leaderboard.
Visit Jina AI →Jina Embeddings v3 is a 570M-parameter Transformer bi-encoder based on the XLM-RoBERTa architecture with several upgrades: rotary position embeddings, FlashAttention 2 and an extended context window of 8,192 tokens. It supports 89 languages with strong cross-lingual retrieval. A distinguishing feature is a set of five task-specific LoRA adapters (retrieval.query, retrieval.passage, separation, classification, text-matching) that are swapped at inference time by passing a 'task' parameter, which improves quality on each downstream task without retraining the base model. The output is a 1024-dimensional vector with Matryoshka representation learning, so truncation to 256 / 512 / 768 dimensions remains semantically meaningful and allows a quality vs. storage trade-off. Training used a multi-stage curriculum on multilingual text-pair data, search-query/document pairs and curated NLI data. Weights are released on Hugging Face under CC-BY-NC 4.0 for research use; commercial use is permitted via the hosted API or a paid commercial licence.
- Parameters
- 570M
- Context
- 8.2K tokens
- 89 languages with strong cross-lingual retrieval
- 8,192-token context window for long-document embedding
- Task-specific LoRA adapters (query, passage, classification, clustering, similarity)
- Matryoshka representation learning: truncate to 256/512/768 dims with graceful degradation
- Top-tier MTEB performance for a model under 1B parameters
- Open weights on Hugging Face for research; commercial via API or paid licence
- Best for: multilingual long-document RAG, semantic search, embedding-heavy SaaS
Multi-stage training on multilingual text pairs, search-query/document pairs, NLI data and curated synthetic data. Exact token count not disclosed.
License: Weights under CC-BY-NC 4.0 on Hugging Face (research only). Commercial use via Jina API or a paid commercial licence.
Known limitations
- Open weights require commercial licence for paid products
- 1024-dim default may be wasteful without Matryoshka truncation
- Task adapter parameter required for best quality on each task
- Long-context retrieval still weaker than chunk-based pipelines on some benchmarks
- Hosted API latency higher than OpenAI text-embedding-3 on small inputs
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 Jina Embeddings v3 (Multilingual) today
Get started with free credits. No credit card required. Access Jina Embeddings v3 (Multilingual) and 100+ other models through a single API.