Access 2,000+ state-of-the-art models by John Snow Labs for understanding clinical and biomedical text or visual documents, using a pay-as-you-go license.
This product is designed to help organizations extract insights from unstructured documents and enable faster, more accurate data analysis. It provides a ready to use Jupyter Hub deploymet that can be used to run John Snow Labs Python library for Healthcare Language Understanding and Visual Language Understanding. The software is designed for data scientists, software developers, and researchers who need to understand unstructured text such as clinical notes, radiology reports, research papers, clinical trial protocols, voice-of-the-patient surveys, lab or sequencing reports - with state-of-the-art accuracy.
There is no limit on the number of documents, models, or pipelines that can be used with this subscription: the software is licensed on a pay-as-you-go basis.
What is included :
John Snow Labs Healthcare Language Understanding Python library, including access to 2,000+ healthcare-specific models covering common tasks like entity recognition, relation extraction, resolving entities to medical terminologies, de-identification, text summarization, question answering, spelling & grammar correction, assertion status detection, embedding calculation, and more.
John Snow Labs Visual Document Understanding Python library, which provides the ability to read PDF, DOCX, DICOM, and various image file formats and automatically extract text, tables, charts, and key-value pairs from forms, using state-of-the-art multimodal models.
Full access to all models and pipelines published on the NLP Models Hub (currently 1,200+ healthcare-specific models and 17,500+ general models).
30+ Ready-to-use Jupyter notebooks that will help you get started with text and image analysis on all major NLP tasks such as text classification, sentiment analysis, named entity recognition, relation extraction, assertion status, entity linking, de-identification, translation, summarization, question answering, spelling and grammar.
Support directly by the data scientists and medical doctors who build the software, as well as access to all new software releases, model updates, and documentation during the subscription period.
Key Features:
Keep up with the state of the art: With new releases every two weeks, our main commitment is to not only provide you with the best accuracy today, but continuously productize newer and better models as they are invented - so that you are always running the most accurate healthcare-specific AI models in history.
Extract deeper medical information: Going beyond the standard of extracting symptoms, treatments, drugs, and anatomy, the included models can extract 400+ medical entities from free-text documents. These include specialized models for oncology, radiology, mental health, pathology, public health, social determinants of health, adverse events, risk factors, and more.
Compose, train, and fine-tune your own models: Compose multiple models into custom pipelines, use transfer learning to train or fine-tune models on your own private data, or use zero-shot learning with prompts, all with a few lines of Python code.
Pay as you go: Only pay for what you use, making the software cost-effective for projects of all sizes, from small-scale research to enterprise-level deployments. Billing is by CPU/hour, not by token, making the software highly cost-effective for large-scale projects.
Who is this product for:
Python developers who need to understand, summarize, de-identify, or extract information from medical text or visual documents
Data scientists in healthcare or life science who build NLP, LLM, or Generative AI solutions
Machine learning engineers who need to train, tune, test, or combine LLM & NLP models
Researchers who need to extract information from unstructured, natural language documents
Software teams building production-grade solutions for understanding and harmonizing clinical, biomedical, patient voice, or other medical information that is coming from text or visual forms
About the Subscription:
By subscribing to the Medical Language Models on Jupyter Hub product, you get access to a preconfigured private Jupyter Hub account containing ready-to-use Jupyter notebooks built for the most popular Healthcare NLP & LLM library in the healthcare and life science industry. You automatically get a pay-as-you-go license key that can be used in the notebooks. You only pay for the time any of the notebooks are running NLP processes, based on the number of processors allocated to your Spark session.
Highlights
Access to state-of-the-art accuracy models designed specifically for the healthcare domain. Supported tasks include summarization, question answering, entity recognition for 400+ entity types, assertion status detection (identify between positive, negative, possible, past, and future facts), clinical relation extraction, clinical entity resolution to SNOMED-CT, ICD-10, CPT, RxNorm, LOINC, NDC, ICD-I, MeSH, UMLS.
Support for Visual Document Understanding. Access to software and models that enable form understanding, table detection and extraction, noisy image enhancement, visual document classification, visual entity recognition, signature detection, and image de-identification.
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.
You pay only for what you use, with three separate metered dimensions. Two dimensions charge per processor per minute: one for medical model usage during annotation or training, and one for OCR and visual document work. The third dimension charges per processor per hour for server usage that runs your annotation or training pipelines. These options are independent, not tiers. Your total scales with how many processors you run and how long each task runs. Charges appear on your AWS bill and reflect actual active usage.
Top-of-mind questions for buyers
What does one processor mean for the per-minute and per-hour charges?
A processor refers to a compute core in your deployed server. Medical model and OCR work meter per vCPU per minute of active processing. Server usage meters per vCPU per hour the pipeline runs. Document Understanding and Healthcare features are billed based on consumption per vCPU.
Am I charged when a pipeline sits idle or the server is stopped?
Charges reflect active usage only. The per-minute dimensions meter time spent on annotation, training, or OCR tasks. The per-hour server dimension meters running pipeline time. Usage data transmits over the internet for accurate metering, so you are billed for actual active processing, not idle capacity.
How do the three metered dimensions combine on my bill?
The three dimensions bill independently and add together. Server usage accrues per processor per hour whenever a pipeline runs. On top of that, medical model tasks and OCR tasks each accrue per processor per minute while active. Tasks using more processors or running longer raise the total.
www.johnsnowlabs.com
Helpful?
Vendor refund policy
No refunds are possible.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
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.
State-of-the-Art Natural Language Processing libraries and Python notebooks tuned for the Healthcare domain. Includes licensed software & models for text mining, DL and Visual model training, tuning, and testing.
The product guarantees state-of-the-art accuracy, native scalability, optimizations for the latest hardware, and the ability to easily compose text and image processing pipelines.
Automate systematic literature reviews end-to-end. Search PubMed,
Semantic Scholar, Europe PMC, OpenAlex, and your own documents; auto-screen against inclusion/exclusion rules; and extract structured, evidence-backed data with medical LLMs - all in your own AWS account.
State-of-the-Art Natural Language Processing libraries and Python notebooks. Includes licensed software & models for text mining, DL and Visual model training, tuning, and testing.
Compact, OCR-specialized vision-language model engineered for state-of-the-art grounded OCR in production document workflows. It is the right model when text recognition AND text location both matter: medical de-identification, form-field extraction, compliance redaction, document anonymization, and any pipeline that needs to act on a specific word at a specific position on a specific page
AI medical assistant has transformed clinical reports and now speeds up patient data analysis
Reviewed on Apr 11, 2026
Review from a verified AWS customer
What is our primary use case?
John Snow Labs is a set of AI software tools and platform mainly for healthcare and life science. I use John Snow Labs for medical purposes, including a medical chatbot that is used for medical queries and analyzing clinical reports.
I use the medical chatbot from John Snow Labs to conduct medical queries, ask patients about any concerns they have, and to extract diseases or symptoms. The chatbot will convert text into structured data.
John Snow Labs can be explored in many ways, including life science, bioinformatics, and genomics. It is also used for drug discovery and research to analyze research papers.
The chatbot from John Snow Labs will extract diseases; if patients have any kind of diabetes, fever, or symptoms, it can analyze them with the help of that tool, making it very beneficial to use that chatbot.
John Snow Labs is a set of AI software tools that is very helpful for healthcare and life sciences. In the future, it will assist in bioinformatics and genomics to detect diseases or genes, identify biomarkers, and help in drug development and discovery.
What is most valuable?
The best feature of John Snow Labs is the medical chatbot, which allows me to ask for queries, medical queries, and medical terminology. I also use it for clinical reports to generate and convert text into structured data. I can easily generate clinical reports and lab reports.
Regarding the medical chatbot feature of John Snow Labs, if I input short text, it will convert it into structured data, generating a complete clinical report, which is very beneficial.
John Snow Labs has positively impacted my organization because there have been many changes since I started using it. The workload is almost very less, and even for the employer, there is less chance to do any work. It is also helpful to get results easily and quickly. Whatever report will be generated takes very less time, and for patients, it is very beneficial to get the report earlier.
What needs improvement?
John Snow Labs is working on different algorithms and technical parts, so improvement is required so that the technical aspects will be less, and the algorithms will be easier to understand. It is very difficult for beginners, thus requiring improvement. Moreover, if there is a predominance of Western data, it would be better if it supports Indian data also.
The user interface of John Snow Labs' software is a bit difficult for beginners to work with. Additionally, more Western data are available compared to India's data, so it would be better to support more Indian data.
For how long have I used the solution?
I have been using John Snow Labs for the last six months.
What do I think about the stability of the solution?
John Snow Labs is stable because it is designed for large-scale processing and has a good accuracy rate. It is also a faster process.
What do I think about the scalability of the solution?
The scalability of John Snow Labs is good because it handles large data and is useful for many users, capable of providing millions of records and data.
How are customer service and support?
Customer support for John Snow Labs is very good because via email and phone, I can easily ask questions. If any kind of technical issues arise, I can reach out easily and inquire about product-related questions also.
How was the initial setup?
It takes almost 30 minutes to generate any kind of report with John Snow Labs. It helps in queries also to ask if any patients have any kind of doubt or questions in their mind; they can ask quickly also, making it less time-consuming.
What was our ROI?
I have seen a return on investment with John Snow Labs because it saves time. The employer is not overwhelmed with work, and they have a lot of time to undertake other tasks. It is indeed a time-saving software that is not time-consuming.
What's my experience with pricing, setup cost, and licensing?
The pricing for John Snow Labs is a little bit high, and the licensing procedure is long, so it really requires time to set up.
What other advice do I have?
I advise others to use John Snow Labs because it is a time-saving software that allows for easy identification and analysis of medical data, clinical reports, and generation of lab reports, along with assistance for research paper analysis. I rate John Snow Labs at eight out of 10 because some improvements are still required, particularly in the technical work that needs to be focused on.
Jiri
AWS licensing server accessible from other systems
Reviewed on May 15, 2024
Review from a verified AWS customer
I have been using John Snow Labs' software for more than four years. This new product is an AWS licensing server giving a fully portable pay-as-you-go license.
You can connect from any system to the licensing server and pay the license for the CPU minutes consumed, including, e.g., from Google colab. The licensing cost will be included in your AWS bill, which is easier to get through procurement.
In terms of features, it includes all that the other software licenses do—you can stay within the Healthcare NLP / Spark NLP and work on the usual pipelines. For me, it is de-identification -> clinical NER extraction -> Assertions -> Clinical coding, plus sometimes relation extractions.