Back to the registry
Agent passport

MedGemma 27B

Tech 42 · Intelligence & Research

No attestation published

Certification per AWS Marketplace.

Provenance reach4 of 12 layers traced

Evidence tier Source Confirmed · 4 captures on record

User ratingNot rated0 reviews on the listing
Runs onUnknownML model
ProvenanceUnknown44% of the provenance layers this product can disclose
Evidence riskHighSign in to see the basis for this band.

What the publisher says

As described on AWS Marketplace.

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.

Show the rest of the publisher’s description (14 more lines)

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

Highlighted by the publisher on AWS Marketplace.

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

Agent build and provenance

See the full provenance

The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.

Compliance

Government
  • FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27

Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.

Plans and pricing as listed

6 listed
ml.g5.12xlarge Inference (Batch)
  • HostHrs
$1.50
ml.g7e.2xlarge Inference (Real-Time)
  • HostHrs
$1.50
ml.g5.24xlarge Inference (Batch)
  • HostHrs
$1.50
ml.g6.12xlarge Inference (Real-Time)
  • HostHrs
$1.50
ml.g6e.12xlarge Inference (Real-Time)
  • HostHrs
$1.50
ml.g7e.4xlarge Inference (Real-Time)
  • HostHrs
$1.50

Refund terms

As stated by the publisher on AWS Marketplace.

Currently we do not support refunds, but you can cancel your subscription to the service at any time.

Sources

Marketplace listingaws.amazon.comSource
App certificationaws.amazon.comSource
CustomEulaCustomEulaSource

Publisher resources

1 link
Deployment guidetech42-org.github.ioSource

Linked repositories

RepositoriesUnknownUnknown

Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.

Pricing
Paid
6 plans listed
Delivery
ML model
Contact us at support@tech42consulting.com or visit our website at tech42consulting.com
Open the source listing ↗

Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.