Voyage 4
Voyage 4 is a mid-sized model in Voyage AI's Voyage 4 family. Voyage AI reports it approaches voyage-3-large retrieval quality with a context window of 32K tokens, Matryoshka dimensions (2048, 1024, 512, 256), and multiple quantization options. All Voyage 4 models share one embedding space, so you can mix models for asymmetric retrieval.
import { embed } from 'ai';
const result = await embed({ model: 'voyage/voyage-4', value: 'Sunny day at the beach',})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
 Voyage AI | 32K | $0.06/M | — | — | 01/15/2026 |
More models by Voyage AI
| Model |
|---|
| 32K | $0.02/M | — | — | | 01/15/2026 | ||||||||
| 32K | $0.12/M | — | — | | 01/15/2026 | ||||||||
| 32K | $0.05/M | — | — | | 08/11/2025 | ||||||||
| 32K | $0.02/M | — | — | | 08/11/2025 | ||||||||
| $0.02/M | — | — | | 05/20/2025 | |||||||||
| $0.06/M | — | — | | 05/20/2025 |
About Voyage 4
Voyage 4 sits at the center of Voyage AI's Voyage 4 lineup, released January 15, 2026. It supports a context window of 32K tokens and occupies the middle ground between the MoE flagship voyage-4-large and the budget-oriented voyage-4-lite.
All Voyage 4 models share one embedding space. You can embed documents with voyage-4-large and run queries through Voyage 4 without maintaining separate vector indices. This asymmetric pattern lets you optimize cost per query while keeping document embeddings at flagship quality.
Voyage 4 supports Matryoshka dimensions (2048, 1024, 512, 256) and quantization-aware training across float32, int8, and binary formats. These compression options apply the same way across all Voyage 4 models, so you can tune storage costs independently of which model you choose for embedding.
What To Consider When Choosing a Provider
- Configuration: When query volume dominates cost, embed the corpus once with
voyage-4-largeand serve queries withvoyage-4-lite, or Voyage 4. Voyage AI reports higher accuracy than symmetric retrieval with smaller models alone. - Configuration: Use Voyage 4 for both queries and documents when you want one model and balanced cost.
- Configuration: Moving from voyage-3.5, voyage-3-large, or older models requires re-embedding because the embedding space differs from Voyage 4.
- Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Voyage 4
Best For
- General-purpose retrieval: You want Voyage 4's shared space and mid-sized efficiency
- Asymmetric setups: Documents use
voyage-4-largeand queries use Voyage 4 to control latency and cost - RAG pipelines: Use Matryoshka dimensions and quantization to cut vector database cost
- Teams moving from voyage-3-large: Want Voyage 4 compatibility and flagship accuracy on the document side
Consider Alternatives When
- Highest average retrieval scores in Voyage AI's published Voyage 4 benchmarks: Use
voyage-4-large(MoE flagship) - Lowest compute for queries: Use
voyage-4-litewhen per-query cost is the binding constraint and voyage-3.5-level accuracy is sufficient - Source-code-only corpora:
voyage-code-3stays purpose-built for code - Multimodal text-and-image embeddings: Pick a model with native image inputs
Conclusion
Voyage 4 is the practical default for teams that want Voyage 4 quality without flagship compute costs. The shared embedding space means you can start here and layer in voyage-4-large for documents or voyage-4-lite for high-volume queries without re-indexing.