Skip to main content

Documentation Index

Fetch the complete documentation index at: https://newscatcherinc-docs.mintlify.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

Each plan includes support for multiple languages, advanced querying capabilities, and comprehensive metadata. Plans differ in their NLP processing capabilities and available features.

Available plans

Plan ID: v3_nlpCore features plus natural language processing for original content and English translations.
Retrieve up to 1,000 articles per request
Filter by article type (headline, opinion, paid content)
URL and domain link filtering
Access predefined top sources by country
Filter by news domain type and source metadata
Filter by robots.txt compliance
Access historical data since 2019
Categorize content across 16 themes (Business, Tech, Politics, and more)
Detect named entities (PER, ORG, LOC, MISC)
Analyze sentiment in titles and content on a -1.0 to 1.0 scale
Get AI-generated article summaries
Enable article clustering and deduplication
Access English translations of non-English content with full NLP processing
NLP features apply to articles indexed from July 2023 onward. Historical articles from 2019 to June 2023 include core metadata only. NLP enrichment for that period is available upon request — contact support@newscatcherapi.com.

Technical specifications

FeatureNLPIPTC TagsEmbeddings
Core features
Article metadata
Article type filtering
Historical data since 2019
Robots.txt compliance filtering
NLP features
Theme classification
Named entity recognition
Sentiment analysis
AI-generated summaries
Clustering and deduplication
Translation features
English translations
NLP on translations
Content tags
IPTC tags
IAB tags
Embeddings
Vector embeddings

Support

For plan selection and pricing, contact our team:
Book a demo to get started.