Generate text and analyze images using Claude language models. Send conversational messages with configurable parameters (model, temperature, system prompt) and receive AI-generated responses, with optional streaming. Execute Python code in a sandboxed environment for data analysis and visualizations. Perform web searches for up-to-date information with cited sources. Use tool calling (function calling) to let Claude invoke structured tools during conversations. Enable extended thinking for complex reasoning tasks. Process and analyze images via vision capabilities. Upload and manage files for multi-session analysis. Connect to remote MCP servers for external system integration. Use agent skills for working with PowerPoint, Excel, Word, and PDF files. Count tokens, cache prompts for reduced latency and cost, create message batches for async processing, and enable citations for source attribution. Administer organizations by managing members, workspaces, invites, API keys, and retrieving usage and cost reports.

Perform AI-optimized web searches, extract content from URLs, run deep multi-step research tasks, and discover entities matching natural language criteria. Provides web-grounded chat completions compatible with OpenAI client libraries. Continuously monitor the web for new information on a configurable schedule and receive webhook notifications when relevant changes are detected. Supports structured JSON output schemas, multiple processing tiers for cost/thoroughness trade-offs, and asynchronous task execution with polling or webhook-based completion tracking.

Unified gateway to 400+ AI/ML models for text generation, image generation, video generation, music generation, speech-to-text, text-to-speech, content moderation, 3D model generation, vision/OCR, embeddings, and AI-powered web search. Generate chat completions and reasoning with models like GPT, Claude, Gemini, DeepSeek, and Llama. Create images from text prompts using Flux, Stable Diffusion, and DALL-E. Generate videos from text or images asynchronously. Convert speech to text and text to speech in 120+ languages. Moderate content for safety classification. Generate 3D objects from text or images. Extract text and structured data from images via OCR. Produce text embeddings for semantic search. Search the web for real-time information. Create AI Assistants for customer support and data analysis. Interact in real time via WebSocket for voice and text. Receive webhook notifications for async operation completion.

Access Ahrefs SEO data including backlink analysis, keyword research, organic traffic estimates, and SERP analysis. Analyze any domain or URL to retrieve Domain Rating, referring domains, organic traffic, top pages, and anchor text distribution. Research keywords with difficulty scores, search volumes, click metrics, and related suggestions. Retrieve current SERP data for competitive analysis. Monitor keyword ranking positions over time and manage Rank Tracker projects. Access Site Audit data including crawl results, detected issues, and health scores. Monitor brand appearances in AI-generated responses across AI platforms via Brand Radar. Manage Keywords Explorer lists and Rank Tracker projects programmatically.

Search, index, and manage records and indices using Algolia's hosted search platform. Perform full-text search with typo tolerance, faceting, filtering, geo-search, and multi-language support. Configure index settings, searchable attributes, custom ranking, synonyms, and query rules. Track user events (clicks, conversions, views, purchases) to power analytics, personalization, and recommendations. Run A/B tests on index configurations. Generate product recommendations including related products, frequently bought together, and trending items. Manage API keys with fine-grained permissions and restrictions. Set up automated data ingestion pipelines from external sources. Crawl websites to extract and index content. Monitor infrastructure status, latency, and indexing performance.

Capture screenshots of any publicly accessible URL using a Chrome-based rendering engine. Configure viewport dimensions, capture full-page scrollable content, or target specific HTML elements via CSS selectors. Supports PNG, JPEG, and WebP output formats. Inject custom CSS and JavaScript to modify page appearance before capture. Pass custom headers, cookies, and proxies to access authenticated or geo-restricted pages. Hide cookie banners automatically. Export screenshots directly to Amazon S3 buckets. Control caching behavior and force fresh captures. Extract HTML content from target pages. Monitor API quota usage and remaining credits.

Access hundreds of AI models from multiple providers (OpenAI, Anthropic, Google, Meta, etc.) through a unified OpenAI-compatible API. Send chat completions to language models with streaming, function calling, and structured output. Generate images, convert text to speech, analyze images with vision models, and create text embeddings. Augment responses with real-time web search grounding, upload documents for RAG-based retrieval, and reduce hallucinations via integrity checking. Discover and filter available models by type, provider, pricing, and performance. Manage routing preferences (cost or performance optimized), configure model pooling for redundancy, enable persistent conversational memory, and track API usage with detailed cost and token analytics.

Scrape websites, bypass anti-bot protections, and extract structured data at scale. Unlock blocked web pages with automatic CAPTCHA solving and proxy rotation. Query search engines (Google, Bing, Yandex, DuckDuckGo) for SERP data with localization and device emulation. Run 120+ pre-built scrapers for popular platforms like Amazon, LinkedIn, and Airbnb. Crawl millions of pages simultaneously. Automate headless browsers via Puppeteer, Playwright, or Selenium with built-in anti-detection. Access pre-collected datasets from 100+ domains. Manage proxy networks across 195 countries with residential, datacenter, ISP, and mobile IPs. Configure zones, manage account settings, and receive webhook notifications on job completion.

Run and manage no-code web scraping robots to extract structured data from websites. Execute on-demand scraping tasks with custom input parameters, retrieve extracted data as structured key-value pairs, and schedule automated monitoring to detect changes on web pages. Perform bulk data extraction across many pages, manage robot cookies for authenticated sessions, and configure webhooks for task completion, data change detection, and export events.

Create and manage cloud-hosted headless browser sessions for web automation. Configure sessions with proxy settings, regional selection, timeouts, and stealth mode for anti-detection. Persist browser state (cookies, localStorage, authentication tokens) across sessions using contexts. Upload Chrome extensions and files to sessions, and retrieve downloaded files. Monitor and debug sessions via CDP logs, session recordings, and live debugger URLs. Retrieve project usage data including browser minutes and proxy bytes consumed.

Search and retrieve global news articles from over 14,000 sources across 70 countries and 18 languages. Fetch latest news in real time, search historical articles by keywords, date range, language, country, category, and domain. Discover available news sources and filter by language or category. Analyze topic trends and sentiment over time. Access reference data for supported languages, regions, and categories.

Scrape and extract structured data from websites using 100+ pre-built templates for eCommerce, search engines, and social media platforms. Route web requests through residential, mobile, ISP, and datacenter proxy pools across 195+ geo-locations. Manage proxy users, whitelisted IPs, and traffic limits via the Public API. Supports real-time and asynchronous scraping with configurable JavaScript rendering, CAPTCHA solving, device emulation, and output parsing (JSON, HTML, Markdown, screenshots). Schedule recurring scrape jobs with delivery via email, webhook, or Google Drive. Track traffic usage, request success rates, and spend across all proxy products. Receive webhook notifications for payment failures, usage threshold alerts, subscription events, and account status changes.

Extract structured data from web pages using AI-powered computer vision and NLP. Automatically classify and parse articles, products, events, jobs, discussions, images, and videos into clean JSON. Search a knowledge graph of 10+ billion entities (organizations, people, articles, products) using Diffbot Query Language (DQL). Enrich person and organization records from minimal identifiers. Analyze natural language text to extract entities, facts, sentiment, and relationships. Crawl entire websites or process bulk URL lists through extraction APIs. Define custom extraction rules with CSS selectors for specific domains. Receive webhook notifications when crawl or bulk jobs complete.

Monitor web page content for changes and receive notifications when updates occur. Create and manage monitors (wachets) for single pages or entire portals with configurable crawling depth. Track specific page sections using XPath selectors, enable JavaScript rendering for dynamic content, and monitor password-protected pages and documents (PDF, DOC). Configure alert conditions, notification channels (email, webhook), and monitoring frequency. Retrieve change history with diff output, browse notifications filtered by date range, and organize monitors into folders.

Create, manage, and execute web scraping jobs to extract structured data from websites. Define sitemaps with CSS selectors and start URLs, run scraping jobs with configurable drivers (fast or full JavaScript), proxies, and timing controls. Monitor job status and data quality, download scraped data in JSON or CSV format, and schedule recurring scraping jobs using cron expressions. Receive webhook notifications when scraping jobs complete. Retrieve account information and remaining page credits.

Scrape and extract data from any website with automatic proxy rotation, headless browser rendering, CAPTCHA solving, and retries. Fetch full rendered HTML or plain text from web pages. Extract specific page elements using CSS selectors. Ask natural language questions about webpage content and receive AI-generated answers. Extract structured JSON fields from pages using AI-powered field descriptions. Execute custom JavaScript on loaded pages to interact with dynamic content. Emulate desktop, mobile, or tablet devices. Route requests through datacenter or residential proxies with geo-targeting support. Send custom headers and cookies for authenticated scraping. Check account credit balance and usage limits.

Search, retrieve, and analyze news articles from thousands of sources across 210+ countries and 86+ languages. Filter news by keywords, date, location, category, language, sentiment, and source. Retrieve top/breaking news headlines clustered by story importance. Extract structured article data from any URL. Discover news sources by name, country, or language. Look up newspaper front page images. Convert news websites to RSS feeds. Perform geo-located news searches by coordinates and radius. Access sentiment scores for articles.

Generate text and chat completions using Writer's Palmyra family of large language models. Create and manage Knowledge Graphs for RAG-based question answering with inline citations. Upload, list, retrieve, and delete files for use with Knowledge Graphs and agents. Analyze images via vision capabilities. Perform web searches for real-time information retrieval. Invoke no-code AI agents as microservices for text generation and research tasks. Use tool calling to integrate custom functions, Knowledge Graph queries, vision, translation, model delegation, and web search within chat conversations. Parse PDFs to extract structured content. Configure guardrails for content safety including toxic content detection and PII protection.

Search for local businesses by keyword, category, location, phone number, price level, and transaction type. Retrieve detailed business information including name, address, phone, photos, ratings, hours, and price levels. Access review excerpts and review highlights for businesses. Provide real-time autocomplete suggestions for business, term, and category searches. Match businesses by name and address to obtain Yelp Business IDs. Use conversational AI chat for natural language local business discovery. Manage business listings, respond to reviews, handle leads, book reservations, and manage advertising programs via partner APIs. Retrieve engagement metrics, advertising performance data, and location analytics. Subscribe to webhooks for review and lead event notifications.

Scrape and extract data from public websites. Fetch page content from any URL with JavaScript rendering, anti-bot bypass, CAPTCHA solving, and premium proxy rotation. Extract structured data using CSS selectors or auto-parsing. Capture screenshots, render pages as Markdown, plain text, or PDF. Target requests from 190+ countries using geolocation. Scrape structured product data from e-commerce platforms like Amazon and Walmart, real estate listings from Zillow and Idealista, and Google search results. Supports session management, device emulation, custom headers, and JavaScript instructions for page interaction.

Scrape and retrieve structured search engine results from Google, Bing, Yandex, and DuckDuckGo in real time. Perform web searches with geotargeting, language, and result count filters. Search Google Images with size, color, and type filters, and perform reverse image lookups. Retrieve Google News, Shopping, Maps/local business, and YouTube search results. Scrape Google Trends data including keyword popularity over time, geographic breakdowns, and related topics. Look up shopping product details by product ID. Retrieve keyword search volume and CPC data. Check account status and remaining API request quota.

Search the web using AI-native neural and keyword search methods. Extract full text, highlights, and summaries from web pages. Find similar pages based on a given URL. Get AI-generated answers to questions with citations. Automate in-depth web research and receive structured results with citations. Build and manage Websets—structured collections of web entities found, verified, and enriched by search agents. Import data into Websets, enrich items with additional structured data, schedule monitors for continuous updates, and export results to CSV, JSON, or XLSX. Configure webhooks for Webset lifecycle events.

Scrape, crawl, search, and extract data from any website. Convert web pages into clean markdown, HTML, screenshots, or structured data with JavaScript rendering and anti-bot handling. Crawl entire websites recursively, search the internet for relevant pages, map site architectures, and use AI-powered extraction to transform unstructured web content into organized data via natural language prompts or JSON schemas. Supports browser automation actions like clicking, scrolling, and form filling, as well as batch scraping of multiple URLs and agent-based autonomous data gathering.

Search, discover, and retrieve detailed information about places and venues from a global database of 100M+ points of interest across 200+ countries. Search places by keyword, category, chain, or geographic area with autocomplete support. Retrieve rich place details including addresses, coordinates, categories, hours, photos, reviews, ratings, and popularity. Match and enrich POI data using GeoTagging/Place Match. Propose edits and flag issues with place data. Manage geofences around venues, coordinates, or custom polygons with bulk operations. Provide personalized place recommendations based on user taste and visit history. Upload and manage geospatial datasets in Foursquare Studio. Access measurement data for campaign insights and optimization. Manage users and authentication tokens. Receive real-time webhook pushes for user check-ins and venue activity.

Convert addresses and place names into geographic coordinates (forward geocoding) and convert latitude/longitude coordinates into human-readable addresses (reverse geocoding). Filter results by country using ISO country codes. Retrieve bounding box coordinates, formatted postal addresses, and distance calculations. Supports JSON and XML response formats with built-in spell check for improved accuracy.