# PyTorch

**Canonical:** https://apis.io/providers/pytorch/  
**Website:** https://pytorch.org  
**APIs profiled:** 5

APIs and resources for PyTorch, an open source machine learning framework for tensor computation and deep learning developed by Meta.

## Kin Score — 13.4 / 100 (emerging)

Scored 2026-08-25 under rubric 0.14.0. Trend: flat (+0.0 from 13.4).

| Facet | Score |
|---|---|
| Discoverability | 55.6 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 10.5 |
| Developer Ergonomics | 16.7 |
| Commercial Clarity | 15.8 |
| Access Clarity | 15.8 |

## Agent readiness — 2.5 (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 | documented |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## Access

Freemium — onboarding: unknown, pricing: freemium, trial: no (confidence: medium).

## APIs (5)

- **PyTorch Core API** — Core PyTorch library for tensor computation and deep learning.
- **TorchVision API** — Computer vision library for PyTorch with datasets, models, and transforms.
- **TorchText API** — Natural language processing library for PyTorch.
- **TorchAudio API** — Audio processing library for PyTorch.
- **PyTorch Hub API** — Pre-trained model repository and discovery API.

## Security (1)

- **Pytorch Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Pytorch Plans Pricing**

## Tags

Artificial Intelligence, Deep Learning, Machine-Learning, Neural Networks, Open-Source, Python

---

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