Voyage 3 Lite
Voyage 3 Lite is Voyage AI's most cost-efficient embedding model, designed for high-volume workloads where per-embedding cost is the primary constraint. It delivers solid retrieval quality at the lowest price point in Voyage's lineup.
Lite is ideal for initial prototyping, large-scale batch embedding, and applications where slight quality tradeoffs are acceptable in exchange for significant cost savings.
Key Features
Lowest cost in Voyage lineup
Solid quality for cost-sensitive workloads
Compact dimensions for storage efficiency
Fast inference for batch processing
Good enough quality for most applications
Ideal Use Cases
High-volume batch embedding at scale
Cost-sensitive retrieval applications
Rapid prototyping and experimentation
Large document collection processing
Technical Specifications
| Dimensions | 512 |
| Modality | Text → Embedding |
| Provider | Voyage AI |
| Category | Embedding |
| Max Input | 32K tokens |
| Tier | Budget |
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-lite", 6 "messages": [ 7 { "role": "user", "content": "Hello, Voyage 3 Lite!" } 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 Lite now
Start using Voyage 3 Lite 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