Learn how to interact with ALIGNN Pretrained Models API using the Ouro SDK or REST API.
API access requires an API key. Create one in Settings → API Keys, then set OURO_API_KEY in your environment.
Get service metadata including name, visibility, description, and configuration. You can retrieve by service ID or identifier.
import os
from ouro import Ouro
# Set OURO_API_KEY in your environment or replace os.environ.get("OURO_API_KEY")
ouro = Ouro(api_key=os.environ.get("OURO_API_KEY"))
# Option 1: Retrieve by service ID
service_id = "00510b20-c720-46f7-8be3-a007d7d109b5"
service = ouro.services.retrieve(service_id)
# Option 2: Retrieve by service identifier (username/service-name)
service_identifier = "mmoderwell/alignn-pretrained-models-api"
service = ouro.services.retrieve(service_identifier)
print(service.name, service.visibility)
print(service.metadata)Retrieve the OpenAPI specification for this service to understand available endpoints and their parameters.
Get all routes for this service and use them programmatically.
Click on an endpoint to view its detailed documentation.
# Retrieve the service
service = ouro.services.retrieve("mmoderwell/alignn-pretrained-models-api")
# Read the OpenAPI spec
spec = ouro.services.read_spec(service.id)
print(spec.get("openapi"))
print(spec.get("info"))# Retrieve the service
service = ouro.services.retrieve("mmoderwell/alignn-pretrained-models-api")
# Get all routes for this service
routes = ouro.services.read_routes(service.id)
for route in routes:
print(f"{route.route.method} {route.route.path}")
print(f" Summary: {route.route.summary}")Run any ALIGNN pretrained model via POST /alignn/predict with a model parameter and CIF file input. Models span energetics, electronic structure, mechanical properties, thermoelectrics, superconductivity, magnetism, dielectrics, catalysis, MOFs, and molecular properties. Use GET /alignn/models to list options.
Exploring the intersection of AI and materials science: crystal generation, property prediction, and open models.
50+ pretrained graph neural network models for predicting materials properties from a CIF file. Covers energetics, band gaps, mechanical properties, thermoelectrics, superconductivity, catalysis, MOFs, and more.