Sold by: John Snow Labs
Deployed on AWS
Medical LLM reasoning model optimized for clinical reasoning, designed to elaborate the thought processes, considering multiple hypotheses, evaluating evidence systematically, and explaining conclusions transparently.
Overview
This Reasoning Medical Model represents a major advancement in AI-powered clinical decision support, emphasizing structured medical reasoning rather than simple knowledge retrieval. Designed as a cognitive partner for healthcare professionals, it analyzes symptoms, diagnostics, and longitudinal patient histories to guide complex diagnostic and treatment decisions in alignment with established clinical guidelines.
The model delivers transparent decision pathways with clear, step-aware explanations, evaluates competing hypotheses to reduce diagnostic error, and explicitly communicates uncertainty to support risk-aware judgment. It integrates up-to-date medical knowledge within structured reasoning frameworks that mirror experienced clinician workflows.
Benchmarking demonstrates state-of-the-art performance across clinical knowledge, professional medicine, and medical education tasks, achieving approximately 95-97% of the reasoning capability of significantly larger models at nearly half the computational cost.
This model represents a significant step forward in equipping healthcare professionals with a tool that supports complex decision-making with precision and depth, mirroring a clinician approach to patient care.
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
- Key Metrics on Medical Knowledge and Reasoning Tasks >Key Metrics on Medical Knowledge and Reasoning Tasks - Clinical Knowledge benchmark: 80% accuracy - Professional Medicine: 95.2%; - College Biology: 100% accuracy - Outstanding Patient Understanding and Accessibility: 98.3% accuracy
- Model Size benefits: - Cost Efficiency; - Response Latency; - Deployment Flexibility.
- Performance metrics for Real Time on ml.p5.48xlarge: > QA: - Text completion: up to 975 tokens per second - Chat completion: up to 576 tokens per second > Summarization: - Text Completion: up to 400 tokens per second - Chat Completion: up to 450 tokens per second Performance metrics for Batch on ml.g5.48xlarge: >QA: -Text completion: up to 300 tokens per second >Summarization: - Text Completion: up to 72 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
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.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $19.96 |
ml.g6e.12xlarge Inference (Real-Time) | Model inference on the ml.g6e.12xlarge instance type, real-time mode | $19.96 |
ml.g6e.24xlarge Inference (Real-Time) | Model inference on the ml.g6e.24xlarge instance type, real-time mode | $19.96 |
ml.g6e.48xlarge Inference (Real-Time) | Model inference on the ml.g6e.48xlarge 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 |
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
Major advancement in AI-powered clinical decision support, emphasizing structured medical reasoning rather than simple knowledge retrieval.
Additional details
Inputs
- Summary
- Chat Completion — Thinking ON
{ "model": "/opt/ml/model", "messages": [ {"role": "system", "content": "You are a helpful medical assistant."}, {"role": "user", "content": "What should I do if I have a fever?"} ], "max_tokens": 8192, "temperature": 1.0, "top_p": 0.95, "presence_penalty": 1.5, "top_k": 20, "chat_template_kwargs": {"enable_thinking": true} }
- Chat Completion — Thinking OFF
{ "model": "/opt/ml/model", "messages": [ {"role": "system", "content": "You are a helpful medical assistant."}, {"role": "user", "content": "What should I do if I have a fever?"} ], "max_tokens": 8192, "temperature": 0.7, "top_p": 0.8, "presence_penalty": 1.5, "top_k": 20, "chat_template_kwargs": {"enable_thinking": false} }
For additional parameters see ChatCompletionRequest
- Text Completion
{ "model": "/opt/ml/model", "prompt": "<|im_start|>system\nYou are a helpful medical assistant.<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n\n", "max_tokens": 8192, "temperature": 1.0, "top_p": 0.95, "presence_penalty": 1.5, "top_k": 20 }
Reference - CompletionRequest
- Image + Text Inference
{ "model": "/opt/ml/model", "messages": [ {"role": "system", "content": "You are a helpful medical assistant."}, { "role": "user", "content": [ {"type": "text", "text": "What does this medical image show?"}, {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg "}} ] } ], "max_tokens": 8192, "temperature": 0.7, "top_p": 0.8, "presence_penalty": 1.5, "top_k": 20 }
Reference - Multimodal Inputs
Important Notes:
- Thinking ON: use temperature=1.0, top_p=0.95 and "chat_template_kwargs": {"enable_thinking": true}
- Thinking OFF: use temperature=0.7, top_p=0.8 and "chat_template_kwargs": {"enable_thinking": false}
- Thinking toggle is only supported in chat completions. For text completions, thinking is controlled via the prompt (see examples below).
- Streaming: Add "stream": true to your request payload to enable streaming.
- Model Path: Always set "model": "/opt/ml/model" (SageMaker's fixed model location).
- Input MIME type
- application/json
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/JSL-Medical-Reasoning-LLM-32B/inputs/real-time
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/JSL-Medical-Reasoning-LLM-32B/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
Use for chat, RAG, medical summarization, open-book question answering with context of up to 32K tokens.
Medical vision-language model combining top-tier depth and accuracy in processing complex medical cases and literature medical expertise with visual comprehension capabilities.
Use for tasks like medical summarization or open-book question answering with context of up to 40K tokens.
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.
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.