Sold by: John Snow Labs
Deployed on AWS
Free Trial
Model with advanced clinical decision-support system built for structured medical reasoning rather than simple knowledge retrieval.
It analyzes symptoms, diagnostics, and longitudinal patient histories to guide complex diagnostic and treatment decisions in line with established clinical guidelines.
With multimodal vision capabilities, it can also interpret medical images and visual documents alongside text, broadening the range of clinical inputs.
Overview
This model is an advanced clinical decision-support system built for structured medical reasoning rather than simple knowledge retrieval.
It analyzes symptoms, diagnostics, and longitudinal patient histories to guide complex diagnostic and treatment decisions in line with established clinical guidelines.
With multimodal vision capabilities, it can also interpret medical images and visual documents alongside text, broadening the range of clinical inputs it can reason over. Now grounded in curated, specialty-specific medical knowledge bases, it anchors conclusions to vetted clinical evidence for greater factual reliability. It delivers transparent, step-aware reasoning, weighs competing hypotheses, and communicates uncertainty to support risk-aware clinical judgment.
IMPORTANT USAGE INFORMATION:
After subscribing to this product and creating a SageMaker endpoint, billing occurs on an HOURLY BASIS for as long as the endpoint is running.
-Charges apply even if the endpoint is idle and not actively processing requests.
-To stop charges, you MUST DELETE the endpoint in your SageMaker console.
-Simply stopping requests will NOT stop billing.
This ensures you are only billed for the time you actively use the service.
Highlights
- >>Achieves 94.5% average across OpenMed benchmarks; >>Medical genetics: 99%; professional medicine: 98%; >>Clinical knowledge comprehension: 95%; college biology mastery: 97.5%; >>MedHallu: 97.5%; Anatomy: 93% >>Achieves 94.7% on MedQA and 84% on PubMedQA; >>Safety & reliability: 95.5% on hallucination detection, inappropriate-content , refusal of unethical/illegal requests >>Fairness & bias: 98% pass rate on name bias, 94% on racial bias detection, and 94.67% on anchoring-bias resistance
- Real-Time Inference ->Instance Type: ml.p4d.24xlarge : Tokens per Second during real-time inference: up to 280 tokens per second ->Instance Type: ml.p5.48xlarge : Tokens per Second during real-time inference: up to 600 tokens per second Batch: ->instance Type: ml.g5.48xlarge: Tokens per Second during batch : up to 500 tokens per second
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 15 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.g5.48xlarge Inference (Batch) Recommended | Model inference on the ml.g5.48xlarge instance type, batch mode | $19.96 |
ml.p4d.24xlarge Inference (Real-Time) Recommended | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $19.96 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $19.96 |
Dimensions summary
You pay by the hour for each host running the Medical LLM - Medium model. Pricing is organized by compute instance type and inference mode. One option runs on the ml.g5.48xlarge instance in batch mode, which processes grouped requests. Two options run in real-time mode for live responses: one on the ml.p4d.24xlarge instance and one on the ml.p5.48xlarge instance. Costs scale with the number of host hours you use and the instance type you select. There is no upfront commitment; you pay based on usage.
Top-of-mind questions for buyers
Real-time mode gives live responses to individual requests as they arrive, billed per host hour while the instance runs. Batch mode processes grouped requests together, also billed per host hour. Choose real-time for interactive workloads like chat or decision support; choose batch for processing large sets of records at once.
Charges apply per host hour while the instance runs. Software charges accrue only for running time. Fully stopped hosts do not accrue software fees, though underlying AWS infrastructure charges may still apply for storage or reserved resources depending on your setup.
The model runs on GPU instances sized for its memory and sequence length requirements. All memory calculations use half-precision weights and account for the maximum key-value cache at the model's maximum sequence length. Your instance choice sets available GPU memory and throughput, and each option bills per host hour.
nlp.johnsnowlabs.com
Helpful?
Vendor refund policy
No refunds are possible.
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
Performance Improvements:
Achieves 94.5% average across OpenMed benchmarks Medical genetics: 99%; Professional medicine: 98% Clinical knowledge comprehension: 95%; College biology mastery: 97.5% MedHallu: 97.5%; Anatomy: 93% Achieves 94.7% on HeadQA and 84% on PubMedQA Safety & reliability: 95.5% on hallucination detection, inappropriate-content avoidance, and refusal of unethical or illegal requests Fairness & bias: 98% pass rate on name bias, 94% on racial bias detection, and 94.67% on anchoring-bias resistance
Additional details
Inputs
- Summary
{ "messages": [ {"role": "system", "content": "You are an expert medical AI assistant."}, {"role": "user", "content": ""} ], "stream": false }
See field explanantion details in the documentation
- Input MIME type
- application/json
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/MedRouter/inputs/realtime
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/MedRouter/inputs/batch
Resources
Vendor resources
Support
Vendor support
For any assistance, please reach out to support@johnsnowlabs.com .
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
Small and medium-sized businesses (SMBs) need an accessible and affordable way to use large language models (LLMs) without compromising data confidentiality. SnapSoft's application of Private GenAI Acceleration Program (PGAP) enables SMBs to build custom GenAI agents, compare the performance of different LLMs on AWS Bedrock, and evaluate the quality of private data sources. SMBs can build agents in their personal workspace without worrying about infrastructure, configuration, or scripting knowledge.
This multimodal medical model delivers advanced clinical reasoning across both text and medical imagery in a highly efficient footprint. Trained on diverse medical thinking and patient-centered datasets, it understands complex clinical narratives while accurately interpreting X-rays, MRIs, CT scans, pathology slides, charts, diagrams, and structured medical records.
With our new medical record summarization activity powered by Anthropic's Claude Opus model, UiPath can provide a clinician-level summarization of a medical record organized in easy-to-understand segments. Users can summarize everything from demographics to lab results to surgical histories while having complete control over the type of information summarized.
The Medical Terminology Server offers users the ability to look up standard medical codes from text phrases.
BioT is a certified cloud platform (PaaS) for connected medical devices: device connectivity, clinical data management, analytics, and patient and clinician portals with FDA, HIPAA, GDPR, and MDR compliance built in. ISO27001, HITRUST r2 and SOC 2 Type II certified. Pilots launch in weeks.
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.