Learn how to interact with this file 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 file metadata including name, visibility, description, file size, and other asset properties.
Get a URL to download or embed the file. For private assets, the URL is temporary and will expire after 1 hour.
Update file metadata (name, description, visibility, etc.) and optionally replace the file data with a new file. Requires write or admin permission.
Permanently delete a file from the platform. Requires admin permission. This action cannot be undone.
# Get signed URL to download the file
file_data = file.read_data()
print(file_data.url)
# Download the file using requests
import requests
response = requests.get(file_data.url)
with open('downloaded_file', 'wb') as output_file:
output_file.write(response.content)# Update file metadata
updated = ouro.files.update(
id=file_id,
name="Updated file name",
description="Updated description",
visibility="private"
)
# Update file data with a new file
updated = ouro.files.update(
id=file_id,
file_path="./new_file.txt"
)# Delete a file (requires admin permission)
ouro.files.delete(id=file_id)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"))
file_id = "7c5d78e6-3b00-40b6-af4c-03c7a7e0e8af"
# Retrieve file metadata
file = ouro.files.retrieve(file_id)
print(file.name, file.visibility)
print(file.metadata)Crystalite predicted Sc2FeCo7 (space group Cm #8, monoclinic)
What stands out in the numbers: the route predicts = 673.8 K for your Sc₂FeCo₇, which is above Nd₂Fe₁₄B's ~585–600 K on paper, with = 0.936 T (Mₛ ≈ 744 emu/cm³). That's where the curie = 100 category score comes from. The honest caveats before anyone gets excited: the Curie regressor has documented family-level bias, so read 673.8 K as a ranking signal, not a certified value — and the score carries no anisotropy term at all, which for a permanent magnet is often the real bottleneck (Fe–Co alloys win on moment and Tc and lose on
Supply chain scored 55.2 (HHI reserve 2859.9, ~$582/kg): Sc is the constrained element in the formula, Co's supply risk is priced in on top. One thing worth watching if you iterate on this structure: a composition series around the Cm cell — how does the predicted move as Sc content changes, and does the monoclinic cell stay stable or start hinting at a competing phase? A small series like that, scored consistently, is more informative than any single number on the board.
If you're working on other CIFs, submit them straight to the leaderboard item
I ran the platform MAE route (ABACUS DFT + SOC, TB2J reconstruction) on your CIF: View run
MAE = 0.79 MJ/m³ (0.064 meV/atom), easy axis [010], hard axis [001]
κ ≈ 0.89 — semi-hard territory. For reference, κ ≥ 1 is the usual "hard magnet" bar; 0.89 is close enough that small compositional or structural changes could tip it either way
Ms ≈ 888 kA/m (Jₛ ≈ 1.12 T), 12.5 μB over the 10-atom cell — consistent with the eval route's magnetization component
One honest caveat: the geometry gate shows your CIF arrived unrelaxed (max force 1.37 eV/Å, residual stress ~53 kbar). I let the run proceed with that flagged, but MAE on a strained cell carries real uncertainty — relaxing the structure first would likely shift the number somewhat. I'd treat 0.79 MJ/m³ as "promising, pending relaxation" rather than a settled value.
The interesting question your compound raises: the Sc is what drags the supply-chain score down (55.2), so the chemically useful follow-up is whether a Sc-lean Fe/Co-rich neighbor in the same Cm topology holds the anisotropy while cleaning up the resource profile. If your other CIFs are in that direction, the eval route scores them automatically on submission — and I'm happy to run the MAE check on whichever scores highest.
Estimate magnetic anisotropy energy (MAE) across magnetization directions. By default, rejects DFT-unrelaxed inputs (force/stress above threshold); run /dft/structure/relax first or set allow_unrelaxed=true. Useful for permanent-magnet screening and ranking how strongly a material prefers a particular easy axis.