Model function

diffdock predicts the 3D structure of how a molecule interacts with a protein, the task commonly described as molecular docking. It is listed as a model under the MIT publisher page on NVIDIA's build catalogue. The listing tags it under Chemistry, nim, BioNemo, Docking and Drug Discovery. It is marked as downloadable alongside the other MIT-published model on that page, Boltz-2.

  • Predicts 3D molecule–protein interaction structures
  • Published by MIT
  • Tagged Chemistry, nim, BioNemo, Docking, Drug Discovery
  • Listed as downloadable

Source: AI Models by MIT | Try NVIDIA NIM APIs

Usage and updates

The MIT model listing records usage figures and an update date for each model. diffdock is shown with 67K API calls in the last 30 days. Its listing states that it was last updated on 15 July 2025.

  • 67K API calls in the last 30 days
  • Last updated 15 July 2025

Source: AI Models by MIT | Try NVIDIA NIM APIs

Placement in the biology catalogue

diffdock also appears on NVIDIA's Explore Biology Models page, which groups models available as NVIDIA NIM microservices. On that page it is placed in the Generative Virtual Screening section and carries the Chemistry, Docking and nim tags. Other models listed in the same biology collection include genmol, molmim, openfold3, Boltz-2, msa-search and openfold2, organised under headings for generative virtual screening, protein structure prediction and protein design.

  • Listed under Generative Virtual Screening
  • Tagged Chemistry, Docking, nim on the biology page
  • Catalogued alongside genmol, molmim, openfold3, Boltz-2, msa-search and openfold2

Sources: Explore Biology Models | Try NVIDIA NIM APIs, AI Models by MIT | Try NVIDIA NIM APIs

Access

diffdock is reachable through NVIDIA's build catalogue, which presents models as NIM APIs that can be tried directly. The MIT publisher page collects the models released under that name, including diffdock. The biology catalogue page provides a route to the same model for users browsing by domain rather than by publisher.

  • Available via NVIDIA NIM APIs
  • Listed on the MIT publisher page at build.nvidia.com/mit
  • Also listed at build.nvidia.com/explore/biology

Sources: AI Models by MIT | Try NVIDIA NIM APIs, Explore Biology Models | Try NVIDIA NIM APIs

Sources

  1. AI Models by MIT | Try NVIDIA NIM APIs https://build.nvidia.com/mit Verified 03 Nov 2026
  2. Explore Biology Models | Try NVIDIA NIM APIs https://build.nvidia.com/explore/biology Verified 03 Nov 2026

Last verified 03 Nov 2026. This entry is compiled from the public web pages listed above. Nothing here is stated that those pages do not, and each of them was read on the date shown.