MedGemma 27B

Approved Data Classifications

Description

MedGemma is Google's open model family for healthcare AI, built on Gemma 3 and tuned for medical and biomedical tasks. The medgemma-27b-it variant is instruction-tuned for clinical-style assistant workflows and supports multimodal input (Text and Image) with Text output. This model has a 32,768-token context window with up to 8,192 output tokens and a May 2024 knowledge cutoff.

As with all medical LLMs, outputs should be reviewed by qualified experts and not used as a standalone diagnostic system.

Capabilities

Model	Release Date	Input	Output	Context Length	Cost (per 1 million tokens)
medgemma-27b-it	May 2024	Text, Image	Text	32,768 (in) / 8,192 (out)	$0.10/1M input $0.30/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "medgemma-27b-it",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI

client = OpenAI(
    api_key="your_api_key",
    base_url="https://api.ai.it.ufl.edu/v1"
)

response = client.chat.completions.create(
    model="medgemma-27b-it", # model to send to the proxy
    messages = [
        { "role": "system", "content": "You are a helpful assistant." },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
)

print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "medgemma-27b-it",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)

---

References

1. Introducing MedGemma (Google Developers Blog) https://developers.googleblog.com/en/introducing-medgemma/
2. Google AI Model Listing: MedGemma 27B
   https://ai.google.dev/gemini-api/docs/models/medgemma-27b-text-it
3. Hugging Face Model Card
   https://huggingface.co/google/medgemma-27b-it