Voyage Code 3
voyage-code-3 turns code into vectors for code search, while voyage-3 serves general text retrieval across languages. Its Matryoshka embeddings allow users to shorten existing vectors without running the model again. Summary written by AI Index from Voyage AI’s own pages.
Prices
1 offering · prices as listedvoyage-code-3| Conditions/ 1M tokens | Input |
|---|---|
| Standard | $0.18 |
Prices from Voyage AI pricing (opens in a new tab) (checked Nov 8, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Shortest vector
- 256
- Vector types
- float, int8, uint8, binary, ubinary
- Model ID
Not stated on Voyage AI’s pages: inputs per request, languages.
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers embedding models yet. MTEB’s results are open (CC0); we will cite them per benchmark, never as a combined score.
Changes
All changes →No changes recorded yet.
Sources
- Text Embeddings (opens in a new tab) docs.voyageai.com · checked Nov 9, 2026
- Voyage AI pricing (opens in a new tab) docs.voyageai.com · checked Nov 8, 2026
- Voyage AI Embedding and Reranking Models Overview - Voyage AI by MongoDB - MongoDB Docs (opens in a new tab) mongodb.com · checked Nov 6, 2026
- voyage-code-3: more accurate code retrieval with lower dimensional, quantized embeddings – Voyage AI (opens in a new tab) blog.voyageai.com · checked Nov 9, 2026
- Voyage AI (opens in a new tab) blog.voyageai.com · checked Nov 8, 2026
Voyage AI’s official policies: data use, privacy, terms →
Voyage AI · United States · voyageai.com
Related models
Snapshots, the same family and other models from this provider