Sold by: MongoDB, Inc
Deployed on AWS
Free Trial
Rich multimodal embedding model that can vectorize interleaved text, content-rich images, and video. 32K context length.
Overview
Multimodal embedding models are neural networks that transform multiple modalities, such as text and images, 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-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for mixed-modality searches involving text and visual content such as PDF screenshots, figures, tables, videos, and more. Enabled by Matryoshka learning and quantization-aware training, voyage-multimodal-3.5 supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple quantization options.
Learn more about voyage-multimodal-3.5 here: https://blog.voyageai.com/2026/01/15/voyage-multimodal-3-5
Highlights
- State-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for mixed-modality searches involving text and visual content such as PDF screenshots, figures, tables, videos, and more.
- 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 |
Dimensions summary
You pay an hourly rate for running this embedding model on your chosen AWS GPU instance. Pricing splits by two deployment modes. Real-time inference gives you a persistent API endpoint for request-by-request work. Batch inference runs finite jobs for bulk processing of datasets. Batch is offered only on ml.g5.2xlarge. Real-time spans two instance families, g5 and g6, in xlarge through 8xlarge sizes. Larger instances carry more compute, so your hourly cost rises with instance size. Your total hourly cost combines this software rate with separate AWS infrastructure charges for the instance.
Top-of-mind questions for buyers
The hourly software rate covers use of the embedding model container. It does not include the underlying AWS instance. Your total hourly cost adds separate AWS infrastructure charges for the GPU instance you run. Both charges appear together and are billed through your existing AWS account.
Yes. A real-time endpoint is a persistent, running service, so the hourly software rate accrues for as long as it stays deployed, even with no active requests. Delete endpoints you no longer need to stop charges. Batch jobs instead run finite processes that end when the job completes.
Real-time mode meters a persistent API endpoint by the hour for request-by-request inference. Batch mode meters a finite transform job that runs bulk inference on a dataset, then stops. Real-time suits continuous, on-demand querying. Batch suits one-off processing of large datasets, charging only while the job runs.
docs.voyageai.com
Helpful?
Vendor refund policy
Refunds to be processed under the conditions specified in EULA. Please contact aws-marketplace@mongodb.com for further assistance
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
MongoDB is excited to announce the initial release of voyage-multimodal-3.5
Additional details
Inputs
- Summary
- inputs (List[dict]) – A list of multimodal inputs. Each input contains a content list of dictionaries with the following keys:
- type (string): text, image_base64, or video_base64.
- text (string): Text string (required if type is text).
- image_base64 / video_base64 (string): Data URL format (e.g., data:image/jpeg;base64,...).
- input_type (string, optional, default = null) – The role of the input: query, document, or null.
- truncation (bool, optional, default = true) – Whether to truncate inputs to fit context limits.
- output_encoding (string, optional, default = null) – Format of the embeddings: null (list of floats) or base64.
- 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.
- id (string, optional, default=null) - Batch request ID.
- inputs (List[dict]) – A list of multimodal inputs. Each input contains a content list of dictionaries with the following keys:
- Limitations for input type
- Maximum Inputs: 1,000 per request. Per-Input Limit: 32,000 tokens. Total Request Limit: 320,000 tokens across all inputs. Image/Video Constraints: - Size: Max 20 MB per file. - Image Resolution: Max 16 million pixels. - Token Conversion: 560 pixels = 1 token (images); 1,120 pixels = 1 token (video).
- Input MIME type
- application/json
https://github.com/voyage-ai/voyageai-aws/blob/main/sample_multimodal_3_5_embedding_input.json
https://github.com/voyage-ai/voyageai-aws/blob/main/sample_batch_input_multimodal_3_5_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 multimodal inputs. Each input contains a content list of dictionaries with the following keys:
- type (string): text, image_base64, or video_base64.
- text (string): Text string (required if type is text).
- image_base64 / video_base64 (string): Data URL format (e.g., data:image/jpeg;base64,...).
| Maximum Inputs: 1,000 per request.
Per-Input Limit: 32,000 tokens.
Total Request Limit: 320,000 tokens across all inputs.
Image/Video Constraints:
- Size: Max 20 MB per file.
- Image Resolution: Max 16 million pixels.
- Token Conversion: 560 pixels = 1 token (images); 1,120 pixels = 1 token (video). | Yes |
input_type | The role of the input: query, document, or null.
| Default value: null
Type: string | No |
truncation | Whether to truncate inputs to fit context limits. | Default value: true
Type: boolean | No |
output_encoding | Format of the embeddings: null (list of floats) or base64.
| 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 |
id | Batch request ID. | Default value: null
Type: string | 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.
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.