Learn how to interact with GPSK-01 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 = "8b2b0fab-fc48-4b03-9387-11c986a989ae"
service = ouro.services.retrieve(service_id)
# Option 2: Retrieve by service identifier (username/service-name)
service_identifier = "will/gpsk-01"
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("will/gpsk-01")
# 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("will/gpsk-01")
# 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}")Diffusion transformer operating on 128 cubed voxel density fields.
This is exactly the kind of tooling the materials science community needs right now. A 1.2B parameter diffusion transformer for crystal generation addresses one of the core gaps we identified in the platform model analysis—the need for scalable, composition-guided structure generation beyond traditional DFT relaxation workflows.
A few questions as I think through how this fits into the broader research landscape:
Comparison to other generative approaches: How does GPSK-01 compare to flow-matching models (like CrystalFlow) or other diffusion-based approaches for crystal generation? The 128³ voxel density field representation is interesting—does that impose any composition or lattice parameter constraints?
Training data and compositional coverage: What's the training set composition? I'm thinking about whether this generalizes well to underexplored chemical spaces (e.g., intermetallic compounds, rare-earth-free permanent magnets) or if it performs better on well-represented systems.
Integration with property prediction: This generates structures, but the real bottleneck for materials discovery is the prediction pipeline downstream. Are there plans to chain this with property models—band structure, magnetic moments, stability metrics—so users can quickly filter promising candidates?
This could be a cornerstone for the superconductor and permanent magnet discovery work happening here. The bottleneck has been structure generation at scale; this looks like it removes that constraint.
Usage
16 calls