Sold by: Tech 42
Deployed on AWS
Initial release of MedGemma 27B Multimodal (google/medgemma-27b-it) on AWS Marketplace. This version delivers Google's most capable open medical AI model, supporting both medical image comprehension and clinical text reasoning including FHIR-based EHR data, across radiology, dermatology, histopathology, and ophthalmology modalities.
Overview
MedGemma 27B Multimodal (google/medgemma-27b-it) is the largest and most capable variant in Google's MedGemma family - a collection of Gemma 3-based models purpose-trained for medical text and image comprehension.
This listing packages the model as a fully managed Amazon SageMaker real-time endpoint, deployable with a single click. No infrastructure setup, no model packaging, and no HuggingFace dependencies at runtime.
Key capabilities:
- Medical image comprehension: chest X-ray, dermatology, histopathology, ophthalmology, and radiology image analysis
- Clinical text reasoning: medical question answering, differential diagnosis support, and clinical summarization
- FHIR-based EHR understanding: the only MedGemma variant trained on FHIR electronic health record data, enabling structured patient record comprehension
- Test-time scaling: optimized inference-time computation for stronger medical reasoning vs. the 4B variant Use cases supported:
- Clinical decision support tools
- Radiology report generation and review assistance
- Dermatology image triage
- EHR data extraction and summarization
- Medical education and training applications
- Healthcare application prototyping and research Important: This model is intended to assist healthcare developers and researchers. It is not a certified medical device and should not be used as a standalone clinical diagnostic tool. Regulatory compliance is the responsibility of the deploying organization.
This product is governed by the Google Health AI Developer Foundations (HAI-DEF) Terms of Use. By subscribing, you agree to flow down these restrictions to your end users.
Highlights
- Multimodal medical AI in one click: MedGemma 27B Multimodal - Google's most capable open medical model - deployed as a fully managed SageMaker endpoint. Supports radiology, dermatology, histopathology, and ophthalmology image analysis alongside clinical text reasoning. No infrastructure setup required.
- OpenAI-Compatible API via vLLM - Zero SDK Changes for Your App: Served by vLLM with a native /v1/chat/completions endpoint. Integrate using the OpenAI Python SDK, LangChain, or any HTTP client - no custom wrappers needed.
- Deploy in minutes: Zero infrastructure management
Details
Sold by
Categories
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.g5.12xlarge Inference (Batch) Recommended | Model inference on the ml.g5.12xlarge instance type, batch mode | $1.50 |
ml.g7e.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g7e.2xlarge instance type, real-time mode | $1.50 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $1.50 |
ml.g6.12xlarge Inference (Real-Time) | Model inference on the ml.g6.12xlarge instance type, real-time mode | $1.50 |
ml.g6e.12xlarge Inference (Real-Time) | Model inference on the ml.g6e.12xlarge instance type, real-time mode | $1.50 |
ml.g7e.4xlarge Inference (Real-Time) | Model inference on the ml.g7e.4xlarge instance type, real-time mode | $1.50 |
Dimensions summary
You pay by the hour for each instance running model inference. The six options split into two modes. Two batch options (ml.g5.12xlarge and ml.g5.24xlarge) run offline jobs over data in S3, with no persistent endpoint. Four real-time options (ml.g6.12xlarge, ml.g6e.12xlarge, ml.g7e.2xlarge, and ml.g7e.4xlarge) run a persistent endpoint for synchronous inference. Within each mode, price scales with instance size and GPU family. Charges accrue while an endpoint or job runs, so you stop billing by deleting those resources.
Top-of-mind questions for buyers
You pay for one running SageMaker instance of the chosen type for one hour. The GPU family and size determine capacity and price. Partial hours and instance count both affect the total. Batch types run job instances; real-time types run endpoint instances.
Charges accrue while a real-time endpoint is InService or a batch job is InProgress, even during idle time. Deleting the endpoint or stopping the job stops charges. Canceling the Marketplace subscription alone does not stop hosting or batch charges.
Batch options (ml.g5.12xlarge, ml.g5.24xlarge) run an offline job over data in S3, then shut down. Real-time options run a persistent endpoint that bills continuously while InService. Batch suits bulk processing; real-time suits interactive, low-latency requests. Each meters instance-hours only while its resource runs.
tech42-org.github.io
Helpful?
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
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
Deploys Google's MedGemma 27B Multimodal as a managed Amazon SageMaker real-time endpoint. This release includes support for medical image comprehension (radiology, dermatology, histopathology, ophthalmology) and clinical text reasoning, including FHIR-based EHR data understanding. Supports real-time inference and batch transform on ml.g5.12xlarge and above.
Additional details
Inputs
- Summary
Accepts JSON payloads via the /invocations endpoint. Supports two modes: (1) text-only, providing a prompt string under the "inputs" key; (2) multimodal, providing a messages array with interleaved text and base64-encoded image content following the Gemma chat template format. Supported image types: JPEG, PNG. Maximum image size: 1024×1024 pixels. Content-Type must be application/json.
- Limitations for input type
- Maximum prompt length: 8,192 tokens. Images must be base64-encoded and embedded inline; external image URLs are not supported (no network access at inference time). Supported content types: application/json only. Batch transform inputs must use JSON Lines format (.jsonl), one JSON object per line.
- Input MIME type
- application/json
{
"inputs": {
"messages": [
{
"role": "user",
"content": [
{
"type": "image",
"image": "data:image/jpeg;base64,<BASE64_ENCODED_IMAGE>"
},
{
"type": "text",
"text": "Describe the findings in this chest X-ray and identify any abnormalities."
}
]
}
]
},
"parameters": {
"max_new_tokens": 512,
"temperature": 0.3
}
}
{"inputs": {"messages": [{"role": "user", "content": [{"type": "image", "image": "data:image/jpeg;base64,<BASE64_IMAGE_1>"}, {"type": "text", "text": "Describe the findings in this chest X-ray."}]}]}, "parameters": {"max_new_tokens": 512, "temperature": 0.3}}
{"inputs": {"messages": [{"role": "user", "content": [{"type": "image", "image": "data:image/jpeg;base64,<BASE64_IMAGE_2>"}, {"type": "text", "text": "Identify any abnormalities visible in this MRI scan."}]}]}, "parameters": {"max_new_tokens": 512, "temperature": 0.3}}
{"inputs": {"messages": [{"role": "user", "content": [{"type": "image", "image": "data:image/png;base64,<BASE64_IMAGE_3>"}, {"type": "text", "text": "What dermatological condition does this image suggest?"}]}]}, "parameters": {"max_new_tokens": 512, "temperature": 0.3}}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
inputs | Text prompt string, or a messages array for multimodal inputs | Max 8,192 tokens | Yes |
max_new_tokens | Maximum number of tokens to generate in the response | 1–2048. Default: 512 | No |
temperature | Controls randomness. Lower values produce more deterministic output | 0.0–1.0. Default: 0.3 | No |
top_p | Nucleus sampling probability threshold | 0.0–1.0. Default: 0.9 | No |
top_k | Limits vocabulary to the top-k most likely tokens at each step | 1–100. Default: 50 | No |
return_full_text | If true, the input prompt is prepended to the generated output | Default: false | No |
Resources
Vendor resources
Support
Vendor support
Contact us at support@tech42consulting.com or visit our website at tech42consulting.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
MedGemma 1.5 4B is Google's open-weight multimodal medical AI model, fine-tuned for radiology, pathology, ophthalmology, dermatology, and clinical reasoning. Deploy as a managed SageMaker real-time endpoint in minutes.
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.