Sold by: Isaacus
Deployed on AWS
A lightweight legal extractive question answering model optimized for extracting metadata and relevant passages from legal documents.
Overview
Kanon Answer Extractor Mini is a lightweight legal extractive question answering model optimized for extracting metadata and relevant passages from legal documents. It ranks second on LegalQAEval below the base Kanon Answer Extractor model but ahead of OpenAI GPT 4.1, Google Gemini, and RoBERTa large. It is 19% more accurate than GPT 4.1.
Kanon Answer Extractor Mini supports a local context window of 512 tokens but can process documents of any length thanks to Isaacus' semchunk semantic chunking algorithm (https://github.com/isaacus-dev/semchunk ).
On a g6.xlarge instance, Kanon Answer Extractor Mini can process up to 236 million tokens per hour, equivalent to roughly 59k average-length legal documents.
Like all other Isaacus SageMaker model deployments, your Kanon Answer Extractor Mini deployment will be fully air-gapped--no data will enter or leave your AWS account.
Conveniently, Isaacus SageMaker models are also compatible with the standard Isaacus Python SDK via the Isaacus SageMaker Python integration (https://docs.isaacus.com/integrations/amazon-sagemaker ).
You can negotiate a discount to Kanon Answer Extractor Mini by contacting us at https://isaacus.com/support .
Highlights
- Ranked second on [LegalQAEval](https://huggingface.co/datasets/isaacus/LegalQAEval) ahead of OpenAI GPT 4.1, Google Gemini, and RoBERTa large, achieving 19% greater accuracy than OpenAI GPT 4.1 at legal information, entity, and metadata extraction.
- Supports legal documents of any length thanks to Isaacus' [semchunk](https://github.com/isaacus-dev/semchunk) semantic chunking algorithm.
- Capable of processing ~59k legal documents (236 million tokens) per hour on a single g6.xlarge instance.
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.g6.xlarge Inference (Batch) Recommended | Model inference on the ml.g6.xlarge instance type, batch mode | $4.99 |
ml.g6.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.xlarge instance type, real-time mode | $4.99 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $4.99 |
ml.g5.2xlarge Inference (Batch) | Model inference on the ml.g5.2xlarge instance type, batch mode | $4.99 |
ml.g5.4xlarge Inference (Batch) | Model inference on the ml.g5.4xlarge instance type, batch mode | $4.99 |
ml.g5.8xlarge Inference (Batch) | Model inference on the ml.g5.8xlarge instance type, batch mode | $4.99 |
ml.g5.16xlarge Inference (Batch) | Model inference on the ml.g5.16xlarge instance type, batch mode | $4.99 |
ml.g6.2xlarge Inference (Batch) | Model inference on the ml.g6.2xlarge instance type, batch mode | $4.99 |
ml.g6.4xlarge Inference (Batch) | Model inference on the ml.g6.4xlarge instance type, batch mode | $4.99 |
ml.g6.8xlarge Inference (Batch) | Model inference on the ml.g6.8xlarge instance type, batch mode | $4.99 |
Dimensions summary
You pay per host hour based on the SageMaker instance you deploy. Choose between two instance families, ml.g5 and ml.g6, in five sizes each: xlarge, 2xlarge, 4xlarge, 8xlarge, and 16xlarge. Larger sizes carry more compute and bill at a higher hourly rate. Each size comes in two inference modes: batch, for processing groups of requests, and real-time, for immediate responses. Pricing scales with your chosen instance size and mode. You pay only for the hours the endpoint runs, with no upfront cost when subscribing.
Top-of-mind questions for buyers
Both meter host hours, but they suit different workloads. Batch mode processes groups of requests together, fitting large document sets you can queue. Real-time mode keeps an endpoint ready for immediate responses, fitting interactive use. You choose the mode when you deploy, and each carries its own hourly rate.
You pay per host hour for the time your endpoint runs, not per request. A real-time endpoint bills for every hour it stays deployed, even when idle. To stop software charges, delete the endpoint. Underlying AWS resource fees may still apply separately.
Yes. These deployments run fully air-gapped within your own AWS account, with no external dependencies. This suits buyers with data sovereignty, compliance, and security requirements. The model server matches the feature set of the hosted API, with requests routed through the SageMaker invocations endpoint.
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
Patched release of this model with version 0.1.4 of the Isaacus SageMaker Model Server, fixing the inability to load models after 19 January 2026 due to an expired Isaacus license key that should now never expire.
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 model 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/extractions/qa with the data {"model":"kanon-answer-extractor-mini","query":"Who is the Governor-General?","texts":["The GG is Sam Mostyn."]}, you could so by sending /invocations the payload {"path":"/v1/extractions/qa","data":{"model":"kanon-answer-extractor-mini","query":"Who is the Governor-General?","texts":["The GG is Sam Mostyn."]}}.
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.
As an extractive question answering model, Kanon Answer Extractor Mini currently only supports the /v1/extractions/qa 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/extractions/qa",
"data": {
"model": "kanon-answer-extractor-mini",
"query": "Who is the Governor-General?",
"texts": [
"The GG is Sam Mostyn."
]
}
}
{
"path": "/v1/extractions/qa",
"data": {
"model": "kanon-answer-extractor-mini",
"query": "Who is the Governor-General?",
"texts": [
"The GG is Sam Mostyn."
]
}
}
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/extractions/qa`). | One of `v1/embeddings`, `/v1/rerankings`, `/v1/extractions/qa`, and `/v1/classifications/universal`. | 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 extractive question answering model optimized for extracting metadata and relevant passages from legal documents.
A state-of-the-art legal embedding model optimized for semantic search, RAG, and document classification, ranked first on the Massive Legal Embedding Benchmark.
Best-in-class legal enrichment, reranking, and embedding models, optimized for legal knowledge graphs and legal RAG.
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.