ChemistryGPU5 credits

TxGemma — Google Therapeutics Reasoning LLM

Ask an LLM about ADMET, hERG, synthesis, binding

TxGemma is Google's therapeutics-specialized LLM with 2B, 9B, and 27B variants. Pretrained on 66 drug-discovery tasks including ADMET, toxicity, reaction prediction, and drug-target interaction. SciRouter exposes it as a reasoning endpoint for MCP-powered agents.

$0.05
per API call
5
credits per call
/v1/interpret/txgemma
API endpoint

Features

ADMET reasoning
hERG / QT interval questions
Lipinski / drug-likeness explanations
Retrosynthesis planning
Pattern-matched pharma knowledge
MCP-ready for agents

Quick Start

TxGemma-9B — Python Examplepython
import requests

result = requests.post(
    "https://scirouter.ai/v1/interpret/txgemma",
    json={
        "query": "Will a compound with MW 600, LogP 5.5 cross the blood-brain barrier?",
    },
    headers={"Authorization": "Bearer sk-sci-your-key"}
).json()["data"]
print(result["answer"])

Use Cases

1

Natural-language ADMET queries from agents

2

Teaching pharmacology with an LLM

3

Drug-target interaction explanations

Learn More

TxGemma Explained: Google's Therapeutics LLM for Drug Discovery

12 min read

Related Tools

ADMET Prediction

Predict absorption, distribution, metabolism, excretion, and toxicity

$0.02/call

ADMET-AI v2

41 ADMET endpoints from Therapeutics Data Commons in one API call

$0.03/call

Start Using TxGemma

500 free credits every month. No credit card required.

Back to all tools