Embed V4.0 is Cohere's latest embedding model, delivering state-of-the-art retrieval performance with support for multiple embedding types — search document, search query, classification, and clustering. This task-specific embedding approach ensures optimal performance for each use case.
V4.0 introduces significant improvements in multilingual retrieval, long-document handling, and domain adaptation, making it one of the most versatile embedding models available for enterprise RAG and search applications.
Key Features
State-of-the-art retrieval benchmarks
Task-specific embedding types
Strong multilingual support (100+ languages)
Improved long-document handling
Compression-friendly representations
Ideal Use Cases
Enterprise RAG with top retrieval accuracy
Multilingual semantic search at scale
Document classification and clustering
Knowledge base and FAQ retrieval
Technical Specifications
| Dimensions | 1024 |
| Modality | Text → Embedding |
| Provider | Cohere |
| Category | Embedding |
| Languages | 100+ |
| Input Types | search_document, search_query, classification, clustering |
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-v4.0", 6 "messages": [ 7 { "role": "user", "content": "Hello, Embed V4.0!" } 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 V4.0 now
Start using Embed V4.0 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