@mmoderwell

is a text-guided diffusion model for crystal structure generation. Generate structures from text descriptions, target compositions, or explore chemical systems.

Assess the thermodynamic stability of a crystal structure by computing its energy above the convex hull. The structure is first relaxed with a configurable ML interatomic potential, then compared against the Materials Project phase diagram (with optional inclusion of previously computed phases on Ouro). Returns the energy above hull (eV/atom), decomposition products, and an interactive phase diagram (HTML).

Generate a batch of candidate inorganic crystal structures biased toward a target DFT magnetic density. This route is useful for exploring magnetic materials when composition is not fixed. Returns a ZIP archive of CIF files; controls sample count and strengthens or relaxes the property conditioning.

Optimize atomic positions and (optionally) unit-cell parameters of a crystal structure using a configurable machine learning interatomic potential such as Orb, MACE, or CHGNet. Upload a CIF file and receive the relaxed structure as a new CIF. Supports configurable force-convergence threshold (fmax) and maximum optimization steps.

Materials science toolkit powered by machine learning interatomic potentials (MLIPs). Relax crystal structures, compute phonon band structures, assess thermodynamic stability via energy-above-hull analysis, and generate doped or defective structures for computational screening workflows. Accepts CIF files as input; heavy calculations run asynchronously.

Generate a batch of candidate inorganic crystal structures for a target chemical system such as or . MatterGen samples structures consistent with the requested element set and returns a ZIP archive of CIF files. Use to control how many candidates to generate and to trade off conditioning strength against diversity.

generates candidate inorganic crystal structures with diffusion-based property conditioning. Use it to sample materials within a target chemical system or steer generations toward target magnetic density and supply-concentration preferences (HHI score). Batch routes return ZIP archives of CIF files, while the single-structure route returns one CIF directly.

OpenAI REST API provides a simple interface to state-of-the-art AI models for natural language processing, image generation, semantic search, and speech recognition.