Artificialintelligenceact APIartificialintelligenceact.eu ↗
Access structured EU AI Act legislation via 11 endpoints. Retrieve articles, recitals, annexes, chapters, keyword search, and the implementation timeline.
What is the Artificialintelligenceact API?
This API provides structured access to the full text of the EU Artificial Intelligence Act through 11 endpoints covering articles, recitals, annexes, chapters, and keyword search. The get_article endpoint returns paragraph-level records with norm type classification and cross-references, while get_implementation_timeline exposes dated regulatory milestones. All major content types support an optional language parameter for multilingual retrieval.
curl -X GET 'https://api.parse.bot/scraper/34a680b3-3ddb-4556-a1e0-636ecd3a360e/get_explorer_index?language=en' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace artificialintelligenceact-eu-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
"""EU AI Act Explorer — structured legal text extraction from the EU AI Act."""
from parse_apis.eu_ai_act_explorer_api import AIAct, ContentNotFound
client = AIAct()
# List all articles and inspect the first few
for article in client.articles.list(limit=5):
print(article.number, article.title)
# Search for high-risk AI provisions
for result in client.articles.search(query="high-risk", limit=3):
print(result.result_title, result.snippet[:80])
# Drill into a specific article's full parsed content
detail = client.article("6").content()
for record in detail.records[:3]:
print(record.unit_id, record.norm_type, record.plain_text[:100])
# Fetch article with related recitals for cross-referencing
enriched = client.article("9").content_with_recitals()
print(enriched.metadata)
for rec in enriched.recitals[:2]:
print(rec.recital_number, rec.text[:80])
# Get a chapter and its associated articles
try:
chapter = client.chapters.get(chapter_number="2")
print(chapter.chapter_title, len(chapter.articles))
except ContentNotFound as exc:
print(f"Chapter not found: {exc}")
# Browse the implementation timeline
for event in client.timelineevents.list(limit=3):
print(event.date, event.description[:80])
print("exercised: articles.list / articles.search / article.content / article.content_with_recitals / chapters.get / timelineevents.list")
Fetch the AI Act Explorer index page metadata and discovered content URLs from the table of contents. Returns the page title, language, and a list of URLs linking to articles, recitals, annexes, and chapters found on the explorer page.
| Param | Type | Description |
|---|---|---|
| language | string | Language code for the page content (e.g. 'en', 'de'). |
{
"type": "object",
"fields": {
"metadata": "object containing source_url, page_title, language, last_updated_date, breadcrumbs, and discovered_urls",
"discovered_urls": "array of URLs to articles, recitals, annexes, and chapters found on the explorer page"
}
}About the Artificialintelligenceact API
What the API Covers
The API covers the complete legislative text published at artificialintelligenceact.eu, organized around the Act's core structural units. You can retrieve individual articles by number (get_article, get_recital, get_annex, get_chapter), enumerate all items in a content type (list_all_articles, list_all_recitals, list_all_annexes), or combine an article with its contextually relevant recitals in a single call (get_article_with_recitals). The explorer index endpoint (get_explorer_index) returns the table-of-contents metadata along with a discovered_urls array pointing to articles, recitals, annexes, and chapters.
Endpoint Response Shapes
get_article returns an array of paragraph-level records, each carrying unit_id, kind, article_number, plain_text, norm_type, keywords, and cross_references — making it straightforward to classify obligations, prohibitions, and permissions programmatically. get_article_with_recitals extends that response with a recitals array containing recital_number, text, and url for each relevant recital. search_act accepts a query string and an optional language code, returning result_title, url, and snippet for each match across articles, recitals, chapters, and annexes.
Implementation Timeline
get_implementation_timeline returns a timeline array of event objects, each with a date, description, and related_content links. This is useful for building compliance calendars or alerting systems tied to the Act's phased rollout dates. The total field at the top level indicates how many distinct timeline events are present.
Language Support
Most content endpoints accept an optional language parameter (e.g. 'en', 'de'), allowing retrieval of the Act text in different EU language versions where available on the source site. The listing endpoints (list_all_articles, list_all_recitals, list_all_annexes) do not accept a language parameter and return language-neutral index data including number, title, and url.
The Artificialintelligenceact API is a managed, monitored endpoint for artificialintelligenceact.eu — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when artificialintelligenceact.eu changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official artificialintelligenceact.eu API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Build a compliance checklist tool that maps
norm_typeclassifications fromget_articleto internal policy obligations. - Generate a regulatory calendar by parsing
dateanddescriptionfields fromget_implementation_timeline. - Cross-reference an article's obligations with explanatory context using
get_article_with_recitalsto retrieve both article text and linked recitals. - Power a legal research search interface using
search_actto surface relevant articles, recitals, and annexes by keyword. - Enumerate the full article index via
list_all_articlesto seed a database of AI Act provisions with titles and canonical URLs. - Compare multilingual versions of a specific provision by calling
get_articlewith differentlanguagecodes for the samearticle_number. - Extract annex contents for high-risk AI system classification analysis using
get_annexwith annex numbers 1 through 3.
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 100 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does artificialintelligenceact.eu have an official developer API?+
What does `get_article` return beyond the plain article text?+
get_article returns paragraph-level records, each including norm_type (classifying the paragraph as an obligation, prohibition, permission, or similar), keywords, cross_references to other provisions, and a unit_id. Navigation links and the source URL are returned in the metadata object.Does the API cover amendment proposals, committee opinions, or non-consolidated versions of the AI Act?+
Can I retrieve all recitals for a given chapter in one call?+
get_chapter returns links to articles within the chapter, and get_article_with_recitals fetches recitals associated with a single article. There is no single endpoint that returns all recitals scoped to a chapter. You can fork this API on Parse and revise it to add a chapter-level recital aggregation endpoint.How current is the legislation text returned by the endpoints?+
metadata object returned by content endpoints includes a last_updated_date field (where available), which reflects the date the source page was last updated. Freshness depends on when the source site publishes updates to the consolidated Act text.