Voyage AI Embeddings
Commercial embedding models built for enterprise-grade semantic search and RAG applications. Features voyage-3 and voyage-3-large models with multimodal support. This is a commercial API service with usage-based pricing.
About this tool
Overview
Voyage AI provides enterprise-grade embedding models optimized for semantic search, RAG applications, and information retrieval. The voyage-3 series models are built for production workloads with high accuracy and throughput.
Key Features
- Multiple Model Sizes: voyage-3, voyage-3-large, and specialized models
- Multimodal Support: Text and image embeddings
- High Performance: Optimized for production throughput
- Specialized Models: Domain-specific models for finance, law, and code
- Batch API: 33% discount for batch processing
Pricing
Standard Pricing (per 1M tokens)
- voyage-3: $0.08
- voyage-3-large: $0.22
- voyage-2: $0.08
- voyage-large-2: $0.22
- Specialized Models (voyage-finance-2, voyage-law-2, voyage-code-2): Custom pricing
Multimodal Pricing
- Text: Per million tokens
- Images: $0.00003 to $0.0012 per image (based on pixel count)
- Pixel Range: 50,000 pixels (minimum) to 2 million pixels (maximum)
Free Tier
- 200 million tokens for most models
- 50 million tokens for specialized models (finance, law, code)
- 150 billion pixels for multimodal models
Batch API Discount
- 33% discount compared to standard endpoints
- 12-hour completion window
AWS Marketplace Pricing Examples
- voyage-2: $0.08 per 1M tokens (ml.g6.xlarge, 36M tokens/hour throughput)
- voyage-3: $0.08 per 1M tokens (ml.g6.xlarge, 40M tokens/hour throughput)
- voyage-3-large: $0.22 per 1M tokens (ml.g6.xlarge, 12.6M tokens/hour throughput)
Model Variants
- voyage-3: General-purpose embedding model
- voyage-3-large: Higher capacity for complex tasks
- voyage-finance-2: Financial domain specialization
- voyage-law-2: Legal domain specialization
- voyage-code-2: Code understanding and search
Cloud Availability
- Voyage AI API
- AWS Marketplace
- Azure Marketplace
- Dedicated instances for enterprise
Use Cases
- Enterprise semantic search
- RAG systems for large organizations
- Domain-specific retrieval (finance, law, code)
- Multimodal search applications
- High-throughput production workloads
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)Universal multimodal embedding model from Jina AI supporting text and images through unified pathway. Built on Qwen2.5-VL-3B-Instruct, outperforms proprietary models on visually rich document retrieval. This is a commercial API with free tier, though OSS weights available.
Commercial text embedding model from Cohere with multilingual support and 1,024-dimensional vectors. Optimized for semantic search and retrieval tasks. This is a commercial API service with pay-per-use pricing.
AI data lake with revolutionary index-on-the-lake technology enabling sub-second queries from S3. Features 10x cost efficiency vs in-memory DBs and 2x faster than alternatives. This is a commercial platform with OSS components.
First fully reproducible open-source text embedding model with 8,192 context length. v2 introduces Mixture-of-Experts architecture for multilingual embeddings. Outperforms OpenAI models on benchmarks. This is an OSS model under Apache 2.0 license.
Microsoft's globally distributed multi-model database with native vector search using DiskANN algorithm. Features <20ms query latency and 43x lower cost vs Pinecone. This is a commercial managed service.
Search and analytics engine with k-nearest neighbor (kNN) search for semantic similarity. Features approximate and exact kNN, HNSW indexing, and advanced quantization. This is commercial with OSS version available.