Providers
Where to actually run the models in the catalog — hosted inference, fine-tuning, and weight downloads.
20 providers
Amazon Web Services
Deploy, fine-tune, and serve biological foundation models like ESM-3 on SageMaker JumpStart and Bedrock, with HealthOmics for genomics workflows.
1 model · 1 with inference · 1 fine-tunable
Azure AI Foundry
Deploy medical-imaging and pathology foundation models to managed Azure endpoints, including MAIRA-2 radiology report generation and Prov-GigaPath.
2 models · 2 with inference
Benchling Model Hub
Run protein and complex structure prediction (AlphaFold 2, Chai-1, Boltz-2, Protenix, OpenFold, BoltzGen) inside the Benchling notebook and registry.
6 models · 6 with inference
Biohub
Run and fine-tune ESM3 and ESMC protein language models on the Forge API for protein structure prediction, design, and embeddings.
2 models · 2 with inference · 2 fine-tunable
BioMap
Run the xTrimoPGLM protein model and xTrimoGene single-cell model through BioMap's API for large-scale protein and transcriptomics tasks.
2 models · 2 with inference
Bioptimus
Run the H-optimus-0 pathology foundation model via Bioptimus's API for histopathology embeddings and computational pathology.
1 model · 1 with inference
Chai Discovery
First-party source for Chai-1: run AlphaFold3-class protein and complex structure prediction via hosted web app and API, with open weights available.
1 model · 1 with inference
genbio.ai
Hosted API and ModelGenerator framework to run and fine-tune the AIDO family across RNA, DNA, protein, and single-cell.
4 models · 4 with inference · 4 fine-tunable
Google Cloud Model Garden
Deploy and fine-tune biological foundation models on managed Vertex AI endpoints: protein structure, therapeutics, medical imaging, and pathology.
8 models · 8 with inference · 2 fine-tunable
Helical
Run and fine-tune single-cell and genomics foundation models — Geneformer, scGPT, Evo 2 — via an open framework, hosted platform, and API.
7 models · 7 with inference · 7 fine-tunable
Hugging Face
Download open weights for protein, DNA, RNA, single-cell, pathology and medical imaging foundation models from Hugging Face model repositories.
258 models · 258 with weights
InstaDeep
Run the Nucleotide Transformer DNA language models via InstaDeep's API for genomics, variant effect, and regulatory sequence prediction.
1 model · 1 with inference
Isomorphic Labs
Gated referral access to AlphaFold 3 for protein and complex structure prediction, plus a non-commercial server for academic research use.
1 model · 1 with inference
Latch.bio
Bioinformatics platform for turnkey AlphaFold 2 structure prediction and Evo genomic-model fine-tuning, extensible via a Python SDK.
2 models · 1 with inference · 1 fine-tunable
Neurosnap
No-code and API inference for protein folding, design, and docking — run AlphaFold 2, RFdiffusion, ProteinMPNN, and RoseTTAFold All-Atom online.
4 models · 4 with inference
NVIDIA BioNeMo / NIM
GPU-accelerated inference and fine-tuning for protein structure, protein design, docking, and genomics foundation models via NIM microservices.
8 models · 8 with inference · 2 fine-tunable
Profluent
Run ProGen3 protein language models and OpenCRISPR gene editors via Profluent's API for protein design, generation, and CRISPR engineering.
2 models · 2 with inference · 1 fine-tunable
Scigantic
Fine-tune open protein and DNA language models — ESM-2, ESMC, DNABERT-2 — from a CSV of sequence-to-label pairs, no GPU setup.
5 models · 5 with inference · 5 fine-tunable
Tamarind Bio
No-code and API inference for protein folding, antibody design, and docking — run ProteinMPNN, AlphaFold 2, RFdiffusion without setup.
5 models · 5 with inference
Zenodo
Download DOI-citable, versioned weights for protein, RNA, genomics, imaging and biosignal foundation models from Zenodo's open repository.
23 models · 23 with weights