Voyage AI's text embedding models convert your text into high-dimensional vectors that capture semantic meaning. The models are inherently multilingual, meaning semantic similarity of texts is irrespective of language. Use the following models to power your AI search applications with state-of-the-art retrieval accuracy.
Available Models
Voyage AI provides the following text embedding models:
General Purpose Models
Model | Context Length | Dimensions | Description |
|---|---|---|---|
| 32,000 tokens | 1024 (default), 256, 512, 2048 | The best general-purpose and multilingual retrieval quality. All embeddings created with the 4 series are compatible with each other. To learn more, see the blog post. |
| 32,000 tokens | 1024 (default), 256, 512, 2048 | Optimized for general-purpose and multilingual retrieval quality. All embeddings created with the 4 series are compatible with each other. To learn more, see the blog post. |
| 32,000 tokens | 1024 (default), 256, 512, 2048 | Optimized for latency and cost. All embeddings created with the 4 series are compatible with each other. To learn more, see the blog post. |
Domain-Specific Models
Model | Context Length | Dimensions | Description |
|---|---|---|---|
| 32,000 tokens | 1024 (default), 256, 512, 2048 | Optimized for code retrieval and agentic-coding applications. Recommended for new code-retrieval use cases. To learn more, see the blog post. |
| 32,000 tokens | 1024 | Optimized for finance retrieval and RAG applications. To learn more, see the blog post. |
| 16,000 tokens | 1024 | Optimized for legal retrieval and RAG applications. To learn more, see the blog post. |
Open Models
Model | Context Length | Dimensions | Description |
|---|---|---|---|
| 32,000 tokens | 512 (default), 128, 256 | Open-weight model available on Hugging Face. All embeddings created with the 4 series are compatible with eachother To learn more, see the blog post. |
Tutorials
For tutorials on using text embeddings, see the following resources: