# Google Cloud AutoML

**Canonical:** https://apis.io/providers/google-cloud-automl/  
**Website:** https://cloud.google.com/automl  
**APIs profiled:** 1

Google Cloud AutoML enables developers with limited machine learning expertise to train high-quality custom models. It provides a suite of products for training custom ML models for translation, natural language, vision, video intelligence, and tabular data using transfer learning and neural architecture search.

## Kin Score — 47.1 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 47.1).

| Facet | Score |
|---|---|
| Discoverability | 68.5 |
| Contract Quality | 60.8 |
| Governance | 9.8 |
| Contract Governance | 9.8 |
| Operational Transparency | 26.3 |
| Developer Ergonomics | 54.8 |
| Commercial Clarity | 47.4 |
| Access Clarity | 47.4 |

## Agent readiness — 29.1 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | yes |
| 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 |

## Access

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

## APIs (1)

- **Google Cloud AutoML Projects API** — The Projects API from Google Cloud AutoML — 4 operation(s) for projects.

## Agentic access (1)

- **Google Cloud Automl Agentic Access** — 7 operations · 4 acting

## Security (2)

- **Google Cloud Automl Domain Security** — TLSv1.3 · HSTS · DMARC
- **Google Cloud Automl Vulnerability Disclosure** — security.txt · contact published

## Plans (1)

- **Google Cloud Automl Plans Pricing**

## Tags

AutoML, Custom Models, Google Cloud, Machine-Learning, Training

---

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