Sold by: MongoDB, Inc
Deployed on AWS
Free Trial
Contextualized chunk embeddings optimized for general-purpose and multilingual retrieval quality. 32K context length.
Overview
Contextualized chunk embedding models are novel neural networks that encode not only the chunks own content, but also capture the contextual information from the full document into numerical vectors. They are a crucial building block for semantic search/retrieval systems and retrieval-augmented generation (RAG) and are responsible for the retrieval quality.
voyage-context-3 is a contextualized chunk embedding model that produces vectors for chunks that capture the full document context without any manual metadata and context augmentation, leading to higher retrieval accuracies than with or without augmentation. On chunk-level and document-level retrieval tasks, voyage-context-3 outperforms OpenAI-v3-large by 14.24% and 7.89%, Cohere-v4 by 12.56% and 5.64%, Jina-v3 late chunking by 23.66% and 20.54%, and contextual retrieval by 6.76% and 2.40%, respectively. Enabled by Matryoshka learning and quantization-aware training, voyage-context-3 supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple quantization options.
Learn more about voyage-context-3 here: https://blog.voyageai.com/2025/07/23/voyage-context-3/
Highlights
- Contextualized chunk embedding model that produces vectors for chunks that capture the full document context without any manual metadata and context augmentation, leading to higher retrieval accuracies than with or without augmentation.
- Supports embeddings of 2048, 1024, 512, and 256 dimensions and offers multiple embedding quantization, including float (32-bit floating point), int8 (8-bit signed integer), uint8 (8-bit unsigned integer), binary (bit-packed int8), and ubinary (bit-packed uint8).
- 32K token context length.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 7 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.2xlarge Inference (Batch) Recommended | Model inference on the ml.g5.2xlarge instance type, batch mode | $3.03 |
ml.g6.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.2xlarge instance type, real-time mode | $2.44 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $2.82 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $3.03 |
ml.g5.4xlarge Inference (Real-Time) | Model inference on the ml.g5.4xlarge instance type, real-time mode | $4.06 |
ml.g5.8xlarge Inference (Real-Time) | Model inference on the ml.g5.8xlarge instance type, real-time mode | $6.12 |
ml.g6.xlarge Inference (Real-Time) | Model inference on the ml.g6.xlarge instance type, real-time mode | $2.25 |
ml.g6.4xlarge Inference (Real-Time) | Model inference on the ml.g6.4xlarge instance type, real-time mode | $3.31 |
ml.g6.8xlarge Inference (Real-Time) | Model inference on the ml.g6.8xlarge instance type, real-time mode | $5.04 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $35.92 |
Dimensions summary
You pay by the hour for running this embedding model on your chosen AWS instance. Pricing scales with instance size and family. Larger sizes (2xlarge through 48xlarge) across the g5, g6, g7e, p5, and p4de GPU families carry different hourly rates. Most instances run in real-time mode, which keeps a persistent API endpoint for request-by-request inference. The ml.g5.2xlarge also offers batch mode, which processes bulk datasets in finite jobs. Your total hourly cost combines software and infrastructure charges. You deploy in your own account, so you pick the instance that fits your workload.
Top-of-mind questions for buyers
You are billed per hour that a model instance runs. Each host hour combines two charges: software pricing for model usage and infrastructure pricing for the AWS instance. Both meter at hourly rates. The total is the sum of these two charges, and rates vary by instance type and region.
Real-time mode keeps a persistent API endpoint running for request-by-request inference, so charges accrue for as long as the endpoint stays active. Batch mode runs finite jobs that process bulk datasets and then stop. Real-time suits steady request traffic; batch suits one-time bulk processing.
No. Canceling your subscription does not terminate existing real-time inference endpoints or batch transform jobs. Active endpoints keep accruing hourly charges until you delete them through the SageMaker console or Studio. To stop costs, shut down endpoints you no longer need.
docs.voyageai.com
Helpful?
Vendor refund policy
Refunds are processed according to the EULA. For assistance, contact aws-marketplace@mongodb.com
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Add support for ml.p5.48xlarge (H100), ml.p4de.24xlarge (A100-80GB), and RTX Pro 6000 Blackwell (ml.g7e.2xlarge/4xlarge/8xlarge/12xlarge/24xlarge/48xlarge) instance types. Remove support for ml.g5.xlarge (A10) and ml.g6.xlarge (L4) instance types due to out-of-memory errors experienced on these instance sizes.
Additional details
Inputs
- Summary
- inputs (List[List[string]]) - A list of lists, where each inner list contains a query, a document, or document chunks to be vectorized.
- input_type (string, optional, default = null) - The role of the input: query, document, or null.
- output_dimension (int, optional, default = 1024) - Supported dimensions: 2048, 1024, 512, 256.
- output_dtype (string, optional, default ="float") - Data type for embeddings: float, int8, uint8, binary, or ubinary.
- encoding_format (string, optional, default = null) - Format in which the embeddings are encoded, other options: base64.
- id (string, optional, default = null) - Batch request ID.
- Limitations for input type
- Max List Length: 1,000. Max Chunks Per Input: 16,000. Max Tokens: 120,000 total tokens per request
- Input MIME type
- application/json
https://github.com/voyage-ai/voyageai-aws/blob/main/sample_contextualized_embedding_input.json
https://github.com/voyage-ai/voyageai-aws/blob/main/sample_batch_input_contextualized_embedding.jsonl
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
inputs | A list of lists, where each inner list contains a query, a document, or document chunks to be vectorized. | Type: List[List[string]]. Max List Length: 1,000. Max Chunks Per Input: 16,000. Max Tokens: 120,000 total tokens per request | Yes |
input_type | The role of the input: query, document, or null. | Default value: null Type: string | No |
output_dimension | Supported dimensions: 2048, 1024, 512, 256. | Default value: 1024 Type: int | No |
output_dtype | Data type for embeddings: float, int8, uint8, binary, or ubinary. | Default value: "float" Type: string | No |
encoding_format | Format in which the embeddings are encoded, other options: base64. | Default value: null Type: string | No |
id | Batch request ID | - | No |
Resources
Vendor resources
Support
Vendor support
Please email us at aws-marketplace@mongodb.com for inquiries and customer support.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Next-generation contextualized chunk embeddings with built-in auto-chunking, overlap support, and extended context length for higher long-document retrieval quality.
A state-of-the-art legal embedding model optimized for semantic search, RAG, and document classification, ranked first on the Massive Legal Embedding Benchmark.
A state-of-the-art reranking model optimized for legal RAG, research, and classification, ranked first on Legal RAG Bench and the Massive Legal Embedding Benchmark (MLEB).
Text embedding model optimized for general-purpose retrieval quality, latency, and cost for AI applications. 32K context length.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.