Features
Scrape URLs to markdown, HTML, screenshots, or branding analysis
Extract structured data using natural language prompts
Search the web and extract results in one API call
Crawl entire websites with configurable depth and breadth
Monitor pages for changes with webhook notifications
Stealth mode for anti-bot bypass (adds 5 credits)
Credit-based usage with top-up packs (never expire)
Playground for testing prompts and formats
JSON schema editor in Playground
Workspaces for team collaboration (v3.4.0)
MCP server for Claude, Cursor, and other MCP clients
API marketplace via Orthogonal (YC W26) for AI agents
Python SDK, JavaScript SDK, CLI
Integrations with LangChain, CrewAI, LlamaIndex, n8n, Zapier, Make
Domain-specific SLLM training on customer data
On-premises or dedicated EU-cloud deployment
Compliance with GDPR and EU AI Act
Collaborative evaluation tools for client teams
PhariaFiles for enterprise file processing
Tokenizer-free model TFree-HAT 7B
Alpha-MoE megakernel for faster tensor-parallel inference
Theoretical inference model for DeepSeek hardware
Secure handling of sensitive documents (90% faster search)
40% faster RFQ processing via AI agents
End-to-end support from ideation to deployment
Integration with internal knowledge worker workflows
