Voyage AI / voyageai/voyage-4-lite
Voyage 4 Lite - access through LLMTR
Voyage 4 Lite targets workloads where you index millions of chunks and unit cost determines the total. It keeps the 32,000-token context window and flexible output dimensions from 256 to 2048 while running at one sixth the price of Voyage 4 Large. It suits volume-heavy work such as log search, product catalog matching and large-scale document indexing.
Technical specifications
| Canonical ID | voyageai/voyage-4-lite |
|---|---|
| Provider | Voyage AI |
| Context window | 32,000 tokens |
| Operations | EMBEDDINGS |
| Modalities | text, embedding |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| EMBEDDINGS | INPUT_TEXT | PER_1M_TOKENS | $0.020000 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"voyageai/voyage-4-lite","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Calculating the cost of indexing millions of chunks with Voyage 4 Lite - Voyage 4 Lite is designed for workloads where you index millions of chunks and unit cost determines the total. This article covers how to calculate that economy of scale and how much quality ceiling is traded away.
Related models
- Voyage 4 Large voyageai/voyage-4-large
- Voyage 4 voyageai/voyage-4
- Voyage Code 4 voyageai/voyage-code-4
- Voyage Code 3 voyageai/voyage-code-3
- Voyage Context 4 voyageai/voyage-context-4
- Voyage Multimodal 3.5 voyageai/voyage-multimodal-3.5
- Voyage Rerank 2.5 voyageai/rerank-2.5
- Voyage Finance 2 voyageai/voyage-finance-2