Discover/Anthropic API
live

Anthropic APIanthropic.com

Fetch announcements and full article content from Anthropic's Claude Fable product page, including model availability status and regulatory updates.

This API takes change requests — .
Endpoints
2
Updated
1mo ago

What is the Anthropic API?

The Anthropic Claude Fable API provides 2 endpoints for extracting structured data from Anthropic's Claude Fable product page. The get_announcements endpoint returns a list of announcement objects — each with title, date, label, summary, and URL — alongside a string describing the current availability status of Claude Fable 5. The get_article endpoint retrieves full article content broken into typed content blocks.

Try it

No input parameters required.

api.parse.bot/scraper/7ca08048-7536-44fd-b5e9-fce06661ddf9/<endpoint>
Ready to send
Fill in the parameters and hit sign in to send to see live response data here.
Call it over HTTPgrab a free API key at signup
curl -X GET 'https://api.parse.bot/scraper/7ca08048-7536-44fd-b5e9-fce06661ddf9/get_announcements' \
  -H 'X-API-Key: $PARSE_API_KEY'
Python SDK · recommended

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 anthropic-com-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.

"""
Anthropic Claude Fable Status API Client
Retrieve announcements and article content from the Anthropic Claude Fable product page.
Get your API key from: https://parse.bot/settings
"""

import os
import requests
from typing import Any


class ParseClient:
    """Client for interacting with the Parse API."""

    def __init__(self, api_key: str | None = None):
        """Initialize the Parse client.
        
        Args:
            api_key: API key for authentication. If not provided, reads from PARSE_API_KEY env var.
        """
        self.base_url = "https://api.parse.bot"
        self.scraper_id = "7ca08048-7536-44fd-b5e9-fce06661ddf9"
        self.api_key = api_key or os.getenv("PARSE_API_KEY")
        if not self.api_key:
            raise ValueError("API key must be provided or set in PARSE_API_KEY environment variable")

    def _call(self, endpoint: str, method: str = "POST", **params: Any) -> dict[str, Any]:
        """Make a request to the Parse API.
        
        Args:
            endpoint: The endpoint name (e.g., 'get_announcements')
            method: HTTP method (GET or POST)
            **params: Query/body parameters for the request
            
        Returns:
            JSON response from the API
        """
        url = f"{self.base_url}/scraper/{self.scraper_id}/{endpoint}"
        headers = {
            "X-API-Key": self.api_key,
            "Content-Type": "application/json"
        }

        if method == "GET":
            response = requests.get(url, headers=headers, params=params)
        elif method == "POST":
            response = requests.post(url, headers=headers, json=params)
        else:
            raise ValueError(f"Unsupported HTTP method: {method}")

        response.raise_for_status()
        return response.json()

    def get_announcements(self) -> dict[str, Any]:
        """Get all announcements from the Claude Fable product page.
        
        Returns:
            Dictionary containing announcements list and availability status
        """
        return self._call("get_announcements", method="GET")

    def get_article(self, article_path: str) -> dict[str, Any]:
        """Get the full content of a news article from the Anthropic website.
        
        Args:
            article_path: The article slug or path (e.g., 'fable-mythos-access')
            
        Returns:
            Dictionary containing article title, date, URL, and structured content
        """
        return self._call("get_article", method="GET", article_path=article_path)


def main():
    """Demonstrate practical usage of the Parse API client."""
    # Initialize the client
    client = ParseClient()

    print("=" * 60)
    print("Claude Fable Status Monitor")
    print("=" * 60)

    # Step 1: Get all announcements
    print("\n📢 Fetching announcements...")
    announcements_data = client.get_announcements()

    # Display availability status
    print(f"\n📊 Current Status: {announcements_data['availability_status']}")

    # Step 2: Process and display announcements
    announcements = announcements_data.get("announcements", [])
    print(f"\n📰 Found {len(announcements)} announcements:\n")

    for i, announcement in enumerate(announcements, 1):
        print(f"{i}. {announcement['title']}")
        print(f"   📅 Date: {announcement['date']}")
        if announcement.get('label'):
            print(f"   🏷️  Label: {announcement['label']}")
        print(f"   📝 Summary: {announcement['summary'][:80]}...")
        print(f"   🔗 URL: {announcement['url']}")
        print()

    # Step 3: Get full content of the most recent announcement
    if announcements:
        latest_announcement = announcements[0]
        article_path = latest_announcement['url'].split('/news/')[-1]

        print("-" * 60)
        print(f"📖 Reading full article: {latest_announcement['title']}")
        print("-" * 60)

        article = client.get_article(article_path)

        print(f"\nTitle: {article['title']}")
        print(f"Date: {article['date']}")
        print(f"URL: {article['url']}")

        print("\n📄 Article Content:")
        print("-" * 40)

        # Display article content with appropriate formatting
        for content_item in article.get("content", []):
            item_type = content_item["type"]
            text = content_item["text"]

            if item_type == "h2":
                print(f"\n## {text}")
            elif item_type == "h3":
                print(f"\n### {text}")
            elif item_type == "p":
                print(f"\n{text}")
            elif item_type == "li":
                print(f"  • {text}")

    print("\n" + "=" * 60)
    print("✅ Monitoring complete")
    print("=" * 60)


if __name__ == "__main__":
    main()
All endpoints · 2 totalmissing one? ·

Get all announcements from the Claude Fable product page, including the current availability status. Returns a list of announcements with titles, dates, labels, summaries, and links to full articles.

Input

No input parameters required.

Response
{
  "type": "object",
  "fields": {
    "announcements": "array of announcement objects with title, date, label, summary, and url",
    "availability_status": "string describing the current availability of Claude Fable 5"
  },
  "sample": {
    "announcements": [
      {
        "url": "https://www.anthropic.com/news/fable-mythos-access",
        "date": "Jun 12, 2026",
        "label": "Update",
        "title": "Claude Fable 5 access unavailable",
        "summary": "We apologize for this disruption to our customers and are working to restore access as soon as possible."
      },
      {
        "url": "https://www.anthropic.com/news/claude-fable-5-mythos-5",
        "date": "Jun 9, 2026",
        "label": null,
        "title": "Claude Fable 5",
        "summary": "Claude Fable 5 introduces our 5th model generation for your most ambitious work. Tackle days-long, complex, and asynchronous tasks previous models couldn’t sustain."
      }
    ],
    "availability_status": "Claude Fable 5 is currently unavailable.Learn more."
  }
}

About the Anthropic API

Announcements Feed

The get_announcements endpoint takes no inputs and returns two top-level fields: announcements and availability_status. Each object in the announcements array includes a title, date, label (a category tag such as a product or policy designation), summary, and url pointing to the full article. The availability_status field is a plain string summarizing the current access state of Claude Fable 5 as presented on the product page — useful for monitoring whether the model is publicly available, restricted, or subject to a government directive.

Full Article Content

The get_article endpoint accepts a single required parameter, article_path, which can be either a short slug like fable-mythos-access or a full path like /news/fable-mythos-access. It returns the article's url, date, title, and a content array. Each element of content is an object with a type field — one of p, li, h2, or h3 — and a text field carrying the actual content. This structure lets you walk the article programmatically without parsing HTML or stripping markup.

Coverage and Scope

Both endpoints are scoped to the Anthropic Claude Fable product page at anthropic.com/claude/fable and its linked news articles. The data reflects what Anthropic publishes on that page: product announcements, model status updates, and any linked editorial or regulatory content. The label field on announcement objects can be used to distinguish categories of updates, such as product releases versus policy or government-related notices.

Reliability & maintenance

The Anthropic API is a managed, monitored endpoint for anthropic.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when anthropic.com 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 anthropic.com 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?+
It's built not to. Every endpoint is health-checked on a schedule with automated test probes. When the source site changes and a check fails, the API is automatically queued for repair and re-verified — that's the self-healing layer. Each API page shows when its endpoints were last verified. And because marketplace APIs are shared, any fix reaches everyone using it.
Is this an official API from the source site?+
No — Parse APIs are independent, managed REST wrappers over publicly available data. That is the point: where a site has no official API (or only a limited one), Parse gives you a maintained, monitored endpoint for that data and keeps it working as the site changes — so you get a stable contract over a source that never promised one.
Can I fix or extend this API myself if I need a new endpoint or field?+
Yes — and you don't have to wait on us. This API was generated by the Parse agent, which stays attached. Describe the change in plain English ("add an endpoint that returns reviews", "fix the price field") in the revise box on the API page or via the revise_api MCP tool, and the agent rebuilds it against the live site in minutes. Contributing the change back to the public API is free.
What happens if I call an endpoint that has an issue?+
Errors are machine-readable: a bad call returns a clean status with the list of available endpoints and a repair hint, so an agent (or you) can recover or trigger a fix instead of failing silently. Confirmed failures feed the automatic repair queue.
Common use cases
  • Monitor the availability_status field to detect when Claude Fable 5 access changes or is restricted
  • Track new announcements by polling get_announcements and diffing the returned date and title fields
  • Retrieve full article text via get_article to feed a newsletter or internal knowledge base
  • Use announcement label fields to filter policy or regulatory notices from product release updates
  • Extract structured article content blocks to index Anthropic news in a search or alerting system
  • Aggregate announcement summary fields to build a changelog of Claude Fable model updates
Pricing & limitsSee full pricing →
TierPriceCredits/monthRate limit
Free$0/mo1005 req/min
Hobby$30/mo1,00020 req/min
Developer$100/mo5,000100 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.

Frequently asked questions
Does Anthropic provide an official developer API for this kind of content?+
Anthropic offers an official API for interacting with Claude models at docs.anthropic.com/en/api, but that API is for running inference, not for reading product page announcements or news articles. There is no official Anthropic developer endpoint for the announcement and article content this API exposes.
What does the `availability_status` field actually contain?+
It is a plain string reflecting the current access description shown on the Claude Fable product page — for example, whether the model is broadly available, in limited access, or subject to an access restriction. It is not a structured enum; the exact wording mirrors what Anthropic publishes on that page at the time of the request.
Can I retrieve articles from other parts of the Anthropic website, not just those linked from the Fable page?+
The get_article endpoint can fetch any article by path on the Anthropic news section as long as you supply the correct article_path slug or full path. Discovery of articles is currently tied to what get_announcements surfaces from the Fable product page — there is no endpoint for browsing the broader Anthropic news index. You can fork this API on Parse and revise it to add a news-index endpoint covering a wider set of articles.
Does `get_announcements` support filtering by label or date range?+
No filtering parameters are currently supported; get_announcements returns all available announcements from the Fable page in a single response. You can filter client-side using the label or date fields on each announcement object. You can fork the API on Parse and revise it to add server-side filtering parameters.
How fresh is the announcement data?+
Each call to get_announcements reflects the current state of the Anthropic Claude Fable product page at the time of the request. There is no cached snapshot with a fixed TTL exposed in the response — the date fields on individual announcements are publication dates from Anthropic, not retrieval timestamps. If freshness guarantees matter, you should poll the endpoint at your own preferred interval.
Page content last updated . Spec covers 2 endpoints from anthropic.com.
Related APIs in News MediaSee all →
news.ycombinator.com API
Browse Hacker News top/new/best/ask/show stories and job posts, search stories by keyword and timeframe, fetch user profiles, retrieve comment threads for a post, and compute basic engagement stats and trending stories.
trends.google.com API
Discover what's trending right now in any country by accessing the top search topics with real-time search volume, growth rates, and related queries. Stay informed on trending categories and see which searches are gaining the most momentum in your target markets.
prnewswire.com API
Access the latest press releases, earnings announcements, and news from PR Newswire across specific categories and organizations, with options to search by keywords or dates. Filter releases by industry, company newsrooms, and subscribe to RSS feeds for real-time updates on corporate news and financial disclosures.
pewresearch.org API
Search and retrieve Pew Research Center publications, reports, and expert profiles across a wide range of topics, including technology, politics, science, religion, and social trends. Access detailed report content, key findings, charts, and methodology information, and filter results by topic, format, or region to stay informed on the latest research and data.
globenewswire.com API
globenewswire.com API
allsides.com API
Get balanced news coverage from multiple political perspectives and discover media bias ratings to understand how outlets lean Left, Center, or Right. Search headlines by topic and perspective to compare how different viewpoints cover the same stories.
top.baidu.com API
Access real-time trending search data from Baidu's Top platform. Retrieve ranked hot search terms, novels, movies, and TV dramas, with support for genre and category filtering across all board tabs.
magzter.com API
Browse and search millions of magazines, newspapers, and stories from Magzter's digital library, then dive into specific publications, issues, and articles by category. Discover detailed information about any magazine or newspaper edition to find exactly what you want to read.