Voyage AI / voyageai/voyage-context-4
Voyage Context 4 - access through LLMTR
Voyage Context 4 vectorizes a document's chunks by seeing all of them at once rather than one at a time. Each chunk's vector therefore carries its position within the document, so phrases such as "this ratio" or "the said party" can resolve against a definition that appears in a different chunk. That context is lost under classic chunking and recovering it measurably improves retrieval over long technical documents and contracts. Unlike the other embedding models, input is supplied as a nested array: the outer list holds documents and each inner list holds that document's chunks.
Technical specifications
| Canonical ID | voyageai/voyage-context-4 |
|---|---|
| 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 | $0.180000 |
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-context-4","messages":[{"role":"user","content":"Hello"}]}'
Related models
- Voyage 4 Large voyageai/voyage-4-large
- Voyage 4 voyageai/voyage-4
- Voyage Code 3 voyageai/voyage-code-3
- Voyage Multimodal 3.5 voyageai/voyage-multimodal-3.5
- Voyage Rerank 2.5 voyageai/rerank-2.5
- Voyage 4 Lite voyageai/voyage-4-lite
- Voyage Finance 2 voyageai/voyage-finance-2
- Voyage Law 2 voyageai/voyage-law-2