Sold by: Isaacus
Deployed on AWS
Best-in-class legal enrichment, reranking, and embedding models, optimized for legal knowledge graphs and legal RAG.
Overview
This bundle packages Isaacus' flagship legal document enrichment, reranking, and embedding models, Kanon 2 Enricher, Kanon 2 Reranker, and Kanon 2 Embedder, into a single deployment optimized for legal knowledge graphs and legal RAG.
Leveraging Kanon 2 Enricher, you can transform raw, unstructured legal documents into rich, highly structured knowledge graphs. With Kanon 2 Reranker and Kanon 2 Embedder, you can then query over your knowledge graphs to deliver relevant search results either directly to end-users or to a generative model that goes on to summarize its findings.
Each model in this bundle is best-in-class. Kanon 2 Enricher qualifies as the world's first hierarchical graphitization model, having no direct analogs or competitors. Kanon 2 Reranker and Kanon 2 Embedder rank first on Legal RAG Bench and the Massive Legal Embedding Benchmark (MLEB), outperforming outperforming Voyage Rerank 2.5 by 7%, Qwen 3 Reranker 8B by 9%, and Voyage 4 Large by 24%.
On a g6e.xlarge instance, Kanon 2 Enricher, Kanon 2 Reranker, and Kanon 2 Embedder all achieve over one billion tokens worth of throughput in an hour, equivalent to 250k average-sized legal documents.
Like all other Isaacus SageMaker AI deployments, this bundle is fully air-gapped--no data enters or leaves your AWS account.
Conveniently, Isaacus SageMaker AI deployments are also compatible with the standard Isaacus Python SDK via the Isaacus SageMaker Python integration (https://docs.isaacus.com/integrations/amazon-sagemaker ).
The list price for an annual subscription to this bundle is US$149,999, however, you may negotiate a discount by contacting us at https://isaacus.com/support .
Highlights
- Best-in-class legal document enrichment, reranking, and embedding capabilities, outperforming outperforming Voyage Rerank 2.5 by 7%, Qwen 3 Reranker 8B by 9%, and Voyage 4 Large by 24%.
- Kanon 2 Enricher and Kanon 2 Reranker support a near-infinite context window thanks to the semchunk semantic chunking algorithm.
- Hourly throughput of over one billion tokens, equivalent to 250k average-sized legal documents.
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
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 | $22.83 |
ml.g6e.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.xlarge instance type, real-time mode | $22.83 |
ml.g6e.2xlarge Inference (Real-Time) | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $22.83 |
ml.g6e.4xlarge Inference (Real-Time) | Model inference on the ml.g6e.4xlarge instance type, real-time mode | $22.83 |
ml.g6e.8xlarge Inference (Real-Time) | Model inference on the ml.g6e.8xlarge instance type, real-time mode | $22.83 |
ml.g6e.16xlarge Inference (Real-Time) | Model inference on the ml.g6e.16xlarge instance type, real-time mode | $22.83 |
Dimensions summary
You pay by the hour for each SageMaker instance running the model bundle. Pricing follows the instance type and inference mode you choose. One option covers batch inference on the ml.g5.2xlarge instance, which processes queued workloads rather than live requests. The other five options cover real-time inference across the ml.g6e family, from xlarge up to 16xlarge. As you move to a larger instance size, the hourly rate scales with the added compute. You control cost by picking the instance that fits your throughput needs. Charges accrue only while your endpoint runs.
Top-of-mind questions for buyers
Batch inference on the ml.g5.2xlarge processes queued workloads instead of live requests. Real-time inference across the ml.g6e family handles live requests where you need immediate responses. Choose batch for scheduled bulk jobs and real-time when your application calls the model interactively.
You pay the hourly rate for each hour the endpoint runs, whether or not it processes requests. Charges accrue based on running time, not request volume. Stopping or deleting the endpoint ends the software charges. Underlying AWS resource fees may apply separately.
No. SageMaker deployments run fully air-gapped inside your own AWS account with no external dependencies. The model server matches the hosted API in features. This suits buyers with data sovereignty, compliance, or security requirements. Your hourly charge covers the instance running inside your account.
isaacus.com
Helpful?
Vendor refund policy
To the maximum extent permitted by law, there are no refunds for consumption of this product.
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.
Additional details
Inputs
- Summary
For a user-friendly walkthrough of how to get started deploying Isaacus models on SageMaker, check out the Isaacus SageMaker quickstart guide on our docs.
This bundle runs on the fully air-gapped Isaacus SageMaker Model Server, which supports all the same functionality as the standard Isaacus API except that requests to the server must be proxied through the /invocations endpoint.
For example, if you wanted to send a POST request to /v1/embeddings with the data {"model": "kanon-2-embedder", "texts": ["This is a confidentiality clause."], "task": "retrieval/query"}, you could so by sending /invocations the payload {"path": "/v1/embeddings", "method": "POST", "data": {"model": "kanon-2-embedder", "texts": ["This is a confidentiality clause."], "task": "retrieval/query"}}.
Likewise, if you wanted to send the request {"model": "kanon-2-reranker", "query": "Who is the Governor-General?", "texts": ["The Governor-General is Sam Mostyn.", "The King is Charles III."]} to /v1/rerankings, you could do so by sending /invocations the payload {"path":"/v1/rerankings", "data": {"model": "kanon-universal-classifier", "query": "Who is the Governor-General?", "texts": ["The Governor-General is Sam Mostyn.", "The King is Charles III."]}}.
This means that minimal code changes are necessary to switch between the online Isaacus API and your own private Isaacus model deployments.
In fact, Python users can use the Isaacus SageMaker Python integration to automatically forward requests to the Isaacus API to SageMaker deployments using the standard Isaacus SDK.
Given that this is a private deployment and that authentication is managed by AWS, Isaacus API keys are not needed and are ignored.
Kanon 2 Enricher is accessible via the /v1/enrichments endpoint, Kanon 2 Reranker via the /v1/rerankings endpoint, and Kanon 2 Embedder via the v1/embeddings endpoint.
- Limitations for input type
- All the same limitations applicable to the Isaacus API except for the need for an API key.
- Input MIME type
- application/json
{
"path": "/v1/embeddings",
"data": {
"model": "kanon-2-embedder",
"texts": [
"Who was the plaintiff in Mabo?"
],
"task": "retrieval/query"
}
}
{"path": "/v1/embeddings","data": {"model": "kanon-2-embedder", "texts": ["This is a confidentiality clause."], "task": "retrieval/query"}}
{"path":"/v1/rerankings","data":{"model":"kanon-universal-classifier","query":"Who is the Governor-General?","texts":["The Governor-General is Sam Mostyn.","The King is Charles III."]}}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
path | The path of the API endpoint being invoked (e.g., `/v1/embeddings`). | One of `/v1/enrichments`, `/v1/rerankings`, or `/v1/embeddings`. | Yes |
method | The HTTP method used for the invocation (e.g., `POST`). Defaults to `POST`. | One of `POST`. | No |
headers | The HTTP headers to include in the invocation request. Defaults to `null`/`None`, in which case no additional headers are sent. | Must be a mapping of strings to strings. | No |
data | The data to be sent as the body of the invocation request. This can be any serializable object. Defaults to `null`/`None`, in which case no body is sent. | - | No |
Resources
Vendor resources
Support
Vendor support
To get in touch with our support team, you can reach out via the support form on our website: https://isaacus.com/support . We endeavor to respond within 24 hours.
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
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 first-of-a-kind enrichment model, capable of transforming unstructured documents into rich, highly structured knowledge graphs.
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).
State-of-the-art legal embedding and reranking models optimized for legal research, legal RAG, and legal document classification.
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.