Sold by: ZeroEntropy
Deployed on AWS
Free Trial
zembed-1 is ZeroEntropy's flagship embedding model for high-accuracy semantic retrieval. It turns text into production-ready vectors for RAG, agents, and search across legal, medical, technical, financial, and code domains.
Overview
ZeroEntropy builds Artificial Specialized Intelligence: task-specific models that make repetitive AI workflows faster, cheaper, and more accurate than general frontier LLMs. zembed-1 converts queries and documents into high-quality vector representations that help retrieval systems surface the most relevant context, reduce noise, and improve downstream answer quality.
Built for production AWS deployments, zembed-1 runs as a SageMaker model package in your own account for private real-time inference or batch embedding jobs. It is designed to pair naturally with ZeroEntropy rerankers, while also working as a standalone embedding model for semantic search, hybrid retrieval, clustering, deduplication, and knowledge-base indexing.
Highlights
- High-accuracy embeddings for semantic retrieval across legal, manufacturing, financial, medical, STEM, conversational, and code search.
- Built for RAG and AI agents - converts queries and documents into vectors that improve recall before reranking or generation.
- Enterprise-ready SageMaker deployment with private inference, batch transform support, and transparent per-instance pricing.
Details
Sold by
Categories
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 | $6.06 |
ml.g6e.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.xlarge instance type, real-time mode | $10.422 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $5.632 |
ml.g5.12xlarge Inference (Batch) | Model inference on the ml.g5.12xlarge instance type, batch mode | $28.36 |
ml.g6.xlarge Inference (Real-Time) | Model inference on the ml.g6.xlarge instance type, real-time mode | $4.507 |
ml.g6.2xlarge Inference (Real-Time) | Model inference on the ml.g6.2xlarge instance type, real-time mode | $4.888 |
ml.g6.4xlarge Inference (Real-Time) | Model inference on the ml.g6.4xlarge instance type, real-time mode | $6.616 |
ml.g6.8xlarge Inference (Real-Time) | Model inference on the ml.g6.8xlarge instance type, real-time mode | $10.072 |
ml.g6.12xlarge Inference (Real-Time) | Model inference on the ml.g6.12xlarge instance type, real-time mode | $23.008 |
ml.g6.16xlarge Inference (Real-Time) | Model inference on the ml.g6.16xlarge instance type, real-time mode | $16.984 |
Dimensions summary
You pay by the host hour for running the zembed-1 embedding model on a chosen instance type. Pricing splits into two modes. Batch mode uses ml.g5 instances in three sizes for offline, bulk processing. Real-time mode uses ml.g6, ml.g6e, ml.g7e, and ml.p5 families across many sizes for live requests. Larger instances within each family carry more compute, so the hourly rate scales with instance size. You select the mode and size that fit your workload and pay only for the hours each instance runs.
Top-of-mind questions for buyers
One HostHrs unit is one hour that a single instance of your chosen type runs the zembed-1 model. You pay for each hour an instance stays active. Charges accrue per running host, so two instances running one hour each count as two host hours.
Software charges meter running host hours only. A fully stopped instance stops accruing software charges. Underlying AWS infrastructure fees for storage or attached resources may still apply separately, but the zembed-1 software charge tracks active running time per host.
Batch mode runs on ml.g5 instances for offline, bulk embedding jobs you start and stop. Real-time mode runs on ml.g6, ml.g6e, ml.g7e, and ml.p5 families to serve live requests continuously. Both bill per host hour, but each fits a different workload pattern.
www.zeroentropy.dev
Helpful?
Vendor refund policy
Please contact support@zeroentropy.dev or ping us on our community Slack/Discord at https://go.zeroentropy.dev/slack and https://go.zeroentropy.dev/discord
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
Initial release of zembed-1.
Additional details
Inputs
- Summary
The input to the embedding model is an embedding_type and a batch of text inputs to embed. embedding_type should be query or document. Example: { "embedding_type": "query", "input": [""], "dimensions": 1280 }
- Limitations for input type
- There is a limit of 1024 inputs per request and 5MB per request as measured by UTF-8 bytes. Individual input strings may be truncated to 16384 bytes. dimensions is optional.
- Input MIME type
- application/json
{"embedding_type":"query","input":["what is the first step in making apple jam"],"dimensions":1280}
{"embedding_type":"query","input":["what is the first step in making apple jam"],"dimensions":1280}
Support
Vendor support
Contact support@zeroentropy.dev
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
zerank-2 is the flagship SOTA reranker by ZeroEntropy, trained with a novel Elo-style pipeline that consistently outperforms every other reranker. By boosting both semantic and lexical search, it delivers the most accurate answers across legal, medical, technical, financial, and code domains.
zerank-1-small is the performant and lowest latency reranker by ZeroEntropy, trained with a novel Elo-style pipeline that consistently outperforms every other reranker. By boosting both semantic and lexical search, it delivers more accurate answers across legal, medical, technical, financial, and code domains.
zerank-1 is the flagship reranker by ZeroEntropy, trained with a novel Elo-style pipeline that consistently outperforms every other reranker. By boosting both semantic and lexical search, it delivers more accurate answers across legal, medical, technical, financial, and code domains.
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.