Embed Multilingual V3.0
Embed Multilingual V3.0 is Cohere's cross-lingual embedding model, producing semantically aligned vectors across 100+ languages. It enables language-independent retrieval where a query in any language can find relevant documents in any other language.
This model is essential for global organizations operating across languages, enabling unified search and retrieval across multilingual document collections without translation preprocessing.
Key Features
100+ language support with cross-lingual alignment
1024-dimensional embeddings
Language-independent retrieval
Strong quality across low-resource languages
Task-specific embedding types
Ideal Use Cases
Global multilingual search systems
Cross-lingual document retrieval
Multilingual customer support automation
International knowledge management
Technical Specifications
| Dimensions | 1024 |
| Modality | Text → Embedding |
| Provider | Cohere |
| Category | Embedding |
| Languages | 100+ |
| Specialty | Cross-lingual retrieval |
API Usage
1 curl -X POST https://api.vincony.com/v1/chat/completions \ 2 -H "Authorization: Bearer YOUR_API_KEY" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "cohere/embed-multilingual-v3.0", 6 "messages": [ 7 { "role": "user", "content": "Hello, Embed Multilingual V3.0!" } 8 ] 9 }'
Replace YOUR_API_KEY with your Vincony API key. OpenAI-compatible endpoint — works with any OpenAI SDK.
Compare with Another Model
Frequently Asked Questions
Try Embed Multilingual V3.0 now
Start using Embed Multilingual V3.0 instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.
More from Cohere
Use ← → to navigate between models · Esc to go back