Voyage Embeddings are Voyage AI’s closed-source retrieval models tuned for RAG. Voyage-3 and voyage-large lead MTEB on multiple retrieval and reranking tasks.
See all models from Voyage AIModels in family
1
Open weight
0
API only
1
Avg score
38.8
Top benchmark
—
Total HF downloads
—
Primary modality
Embedding
First release
Jan 2025
Latest release
Jan 2025
Every release in the Voyage Embeddings family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | voyage-3-largeAPI | embedding | DD38.8 | — | Jan 2025 |
When each release shipped, newest first. Useful for tracking version cadence.
Jan 7
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Closed-source releases accessed through Voyage AI’s API.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | voyage-3-largeAPI | embedding | DD38.8 | — | Jan 2025 |
The Voyage Embeddings family is a series of AI models from Voyage AI. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, voyage-3-large is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Provider
See every model from a lab side by side, with aggregate stats. Useful when you want a cross-family view of one provider.
