Sold by: AUM Labs
Deployed on AWS
Free Trial
https://tfhub.dev/google/universal-sentence-encoder-multilingual/1
5
Overview
The Universal Sentence Encoder encodes text into high-dimensional vectors that can be used for text classification, semantic similarity, clustering and other natural language tasks.
The model is trained and optimized for greater-than-word length text, such as sentences, phrases or short paragraphs. It is trained on a variety of data sources and a variety of tasks with the aim of dynamically accommodating a wide variety of natural language understanding tasks. The input is variable-length text and the output is a 512-dimensional vector.
The model supports text in 16 languages (Arabic, Chinese-simplified, Chinese-traditional, English, French, German, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Thai, Turkish, Russian). The language of the text input does not need to be specified.
Highlights
- Covers 16 languages, showing strong performance on cross-lingual retrieval.
- The model is intended to be used for text classification, text clustering, semantic textual similarity retrieval, cross-lingual text retrieval, etc.
- Developed by researchers at Google, 2019
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 5 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.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $0.10 |
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.10 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $0.10 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $0.10 |
ml.m5.12xlarge Inference (Batch) | Model inference on the ml.m5.12xlarge instance type, batch mode | $0.10 |
ml.m5.large Inference (Batch) | Model inference on the ml.m5.large instance type, batch mode | $0.10 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $0.10 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $0.10 |
ml.m4.10xlarge Inference (Batch) | Model inference on the ml.m4.10xlarge instance type, batch mode | $0.10 |
ml.m5.24xlarge Inference (Batch) | Model inference on the ml.m5.24xlarge instance type, batch mode | $0.10 |
Dimensions summary
You pay by the hour for each host you run, based on the instance type you choose. Pricing splits into two modes: batch inference and real-time inference. Batch mode covers m4 and m5 instance families across sizes from large to 24xlarge. Real-time mode adds the m5d family alongside m4 and m5. Larger instance sizes carry higher hourly rates because they provide more compute. You select the mode and instance size that fit your workload, and you are billed only for the hours each host runs. No per-token charges apply.
Top-of-mind questions for buyers
Both meter host-hours, but they suit different workloads. Batch mode processes grouped requests in scheduled runs, so you pay only while the batch job runs. Real-time mode keeps a host live to answer requests as they arrive, so charges accrue for the full period the endpoint stays active.
One host-hour is one running instance of the chosen type for one hour. Charges accrue for every hour a host stays active, even without incoming requests. Real-time endpoints run continuously until you stop them. Batch hosts run only during the job. Fully stopped hosts do not accrue software charges.
No. Billing is a flat hourly rate per running host, with no per-token or per-request fees. Your cost depends only on the instance type you select and the number of hours each host runs. Processing more sentences within those hours does not raise the software charge.
aumlabs.ai
Helpful?
Vendor refund policy
Thank you for purchasing USE Embedding API on AWS Marketplace. We strive to ensure customer satisfaction with our services. If you have issues accessing the service contact us at support@aumlabs.ai
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
Additional details
Inputs
- Summary
This model can analyze text passed as json or json text files stored in Amazon S3 bucket.
- Limitations for input type
- Maximum payload size for endpoint invocation is 5MB while the maximum payload size for batch inference is 100 MB.
- Input MIME type
- application/json
{
"text": [
"Puppies are nice.",
"I enjoy taking long walks along the beach with my dog."
]
}
https://github.com/aumlabs/aws-marketplace-listing/blob/main/sagemaker/use-multilingual/data/input/batch/input.jsonl
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
text | An array of text. The text can be in any of the supported languages: Arabic, Chinese-simplified, Chinese-traditional, English, French, German, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Thai, Turkish, Russian. | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
AWS Infrastructure 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.
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
Upbound Universal Crossplane (UXP) is Upbound's official enterprise-grade Crossplane distribution. It's free, open source, and fully conformant with upstream Crossplane.
VyOS is an Enterprise-Grade Open Source Networking Platform for Bare Metal, Cloud, and Edge
Parallel Universe is the industry's only SQL server to feature Parallel Query and Parallel Network Query (Distributed Query) with unprecedented speed, utilizing multiple CPU/cores and multiple server hardware while maintaining full compatibility with MySQL and Percona servers.
Parallel Universe is the industry's only SQL server to feature Parallel Query and Parallel Network Query (Distributed Query) with unprecedented speed, utilizing multiple CPU/cores and multiple server hardware while maintaining full compatibility with MySQL and Percona servers.
Infoblox Universal DDI Product Suite: the most advanced, comprehensive portfolio of DNS, DHCP and IP address management solutions for hybrid, multi-cloud environments.
Customer reviews
John Smith
Game Changer
Reviewed on Jan 20, 2025
Review from a verified AWS customer
AUM labs transformed our approach to AI deployment. The seamless integration and the ability to run inference APIs in our private cloud was a game changer for us and further helped us keep our data secure.