voyage-4 is a general-purpose, multilingual embedding model optimized for high-performance semantic search in production environments. It offers a strong balance of retrieval accuracy, latency, and cost efficiency, making it a versatile choice for a wide range of search and retrieval applications.
voyage-4 shares an embedding space with the rest of the Voyage 4 family, allowing teams to mix models across indexing and querying. It supports output dimensions of 2048, 1024, 512, and 256, as well as multiple quantization options for efficient deployment at scale.
On-demand DeploymentDocs | On-demand deployments allow you to use Voyage 4 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
All Voyage 4 models share the same embedding space and support the same output dimensions: 2048, 1024, 512, and 256. They also support the same quantization options.
The main difference is model size. Larger models provide higher retrieval accuracy, while smaller models are optimized for lower latency and greater cost efficiency. Because the models share a compatible embedding space, teams can mix and match them across their retrieval pipeline to optimize for accuracy, latency, and cost.
General-purpose retrieval. The bar chart below compares the average retrieval quality of the Voyage 4 series of models along with Gemini Embedding 001, Cohere Embed v4, and OpenAI v3 Large. Overall, voyage-4-large is the top-performing model, surpassing voyage-4, voyage-4-lite, Gemini Embedding 001, Cohere Embed v4, and OpenAI v3 Large by an average of 1.87%, 4.80%, 3.87%, 8.20%, and 14.05%, respectively.
Asymmetric retrieval means using different embedding models for queries and documents while keeping the embeddings compatible in the same vector space.
For example, you can embed documents with voyage-4-large to maximize index accuracy, then embed user queries with voyage-4-lite to reduce query-time latency and cost. Since Voyage 4 models share an embedding space, these embeddings can be used together in the same retrieval workflow.
This approach is useful when you want to preserve strong search accuracy while improving real-time latency or reducing operating costs.
Voyage 4 models support five output data types: float, int8, uint8, binary, and ubinary.
These lower-precision formats can significantly reduce storage and retrieval costs while preserving retrieval accuracy, thanks to quantization-aware training.
