Voyage 3 is Voyage AI's balanced embedding model, delivering strong retrieval quality at a lower cost than the Large variant. It represents the sweet spot in Voyage's lineup — excellent performance for most retrieval applications without the premium pricing of the flagship model.
Voyage 3 is the default recommendation for production RAG systems and semantic search engines where quality matters but cost efficiency is also important.
Key Features
Balanced quality and cost for production use
Strong retrieval across diverse content types
Efficient dimensionality for storage and compute
Good multilingual capabilities
Versatile across retrieval, classification, and clustering
Ideal Use Cases
Production RAG systems at scale
Cost-efficient semantic search
Content recommendation engines
Document classification and routing
Technical Specifications
| Dimensions | 1024 |
| Modality | Text → Embedding |
| Provider | Voyage AI |
| Category | Embedding |
| Max Input | 32K tokens |
| Tier | Balanced |
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": "voyage/voyage-3", 6 "messages": [ 7 { "role": "user", "content": "Hello, Voyage 3!" } 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 Voyage 3 now
Start using Voyage 3 instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.
More from Voyage
Use ← → to navigate between models · Esc to go back