# Recursion Pharmaceuticals

**Canonical:** https://apis.io/providers/recursion-pharmaceuticals/  
**Website:** https://www.recursion.com  
**APIs profiled:** 0

Recursion Pharmaceuticals (NASDAQ: RXRX) is a Salt Lake City-based AI-enabled drug discovery company that operates the Recursion Operating System (Recursion OS), a vertically integrated platform combining automated wet-lab cellular phenomics, transcriptomics (Trekseq), proteomics, ADME, chemistry, and patient data with machine learning to map biology and design drug candidates. The platform runs on BioHive-2, a NVIDIA-built supercomputer ranked among the top global systems and dedicated to biopharma workloads, and is fed by 50+ petabytes of proprietary biological and chemical data. In November 2024 Recursion completed the acquisition of Exscientia, folding Exscientia's generative AI chemistry, Centaur Chemist, and clinical pipeline into the combined company; Recursion now runs more than 10 clinical and preclinical programs (REC-4881 for FAP, REC-3565 MALT1 inhibitor, REC-1245 RBM39 for biomarker-enriched solid tumors and lymphomas, REC-617 CDK7 inhibitor, REC-994 for cerebral cavernous malformation, REC-2282 for NF2- mutated meningiomas, REC-4209 for IPF, REC-7735 for HSD obesity), 10+ advanced discovery programs, and 10+ partnered programs across Roche (Genentech), Bayer, Sanofi, and Merck KGaA (Darmstadt). Recursion does not currently expose paid commercial APIs to external developers; assets and data access are delivered through licensing, scientific collaborations, and the MapApp web product. Externally, Recursion ships substantial open tooling: the RxRx family of open phenomics datasets (RxRx1, RxRx2, RxRx3, RxRx3-core, RxRx19a, RxRx19b) hosted at rxrx.ai and Hugging Face, the OpenPhenom-S/16 foundation model (released on Hugging Face and Google Cloud's Model Garden, with Phenom-Beta on NVIDIA BioNeMo), the MolE molecular foundation model, the gflownet library for graph and molecular generative modeling, SynFlowNet/synflownet-boltz for retrosynthesis-aware molecular design, maes_microscopy (NeurIPS 2023 spotlight masked autoencoders for cell microscopy), and rxrx1-utils for the NeurIPS 2019 CellSignal competition. The combination positions Recursion as a Tier-2 AI drug discovery provider with no commercial API surface but a meaningful open-source and open-model presence aimed at the computational biology research community.

## Kin Score — 3.7 / 100 (minimal)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 3.7).

| Facet | Score |
|---|---|
| Discoverability | 50.0 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 0.0 |
| Commercial Clarity | 0.0 |
| Access Clarity | 0.0 |

Regulatory layer — **Health**: 7.5 (matched via tags).

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Security (1)

- **Recursion Pharmaceuticals Domain Security** — TLSv1.3 · DMARC

## Tags

Artificial Intelligence, Drug Discovery, Biotech, Pharmaceuticals, Phenomics, Cellular Imaging, Transcriptomics, Proteomics, Chemistry, Machine-Learning, Foundation Models, Open Datasets, Open Source Models, Generative Chemistry, Oncology, Rare Disease, Clinical Trials, BioHive, Recursion OS, MOSAIC, MapApp, OpenPhenom, MolE, GFlowNet, RxRx, Exscientia

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/recursion-pharmaceuticals/). Scores are computed from the provider's own public artifacts under a published rubric.