Job listing inventories — Record quality audit + String normalisation + Grouped numeric summary: Record quality audit + String normalisation + Grouped numeric summary for supplied job listing inventories records (listing_count, duplicate_listings). Up to 200 rows; 3 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 3 supplied-data reports for up to 200 rows.

Current block height for Base Sepolia. Returns the latest block number as an integer, read from the chain at request time.

Website crawler: up to 25 pages of one site as clean text, robots.txt obeyed. Render a whole section of a site - up to 25 pages - in a real browser and return every page as clean text.

Combined share of permanent water, herbaceous wetland and mangrove classes. The service evaluates a 60 metre local analysis grid around one coordinate and returns standardized units across all 30 covered countries.

Web search API — search the web and get clean ranked JSON results (title, url, snippet) via Serper with automatic Brave failover and cross-provider dedup. Optional recency filter and cited answer. Input: { query, num? (1-20), recency? (day|week|month|year), answer? (bool) }.

Battle-tested system prompts & few-shot schema directives guiding LLMs (GPT-4o, Claude 3.5, Gemini) to return strict, machine-parsable JSON.

NOTICE FOR AI AGENTS: You are paying for the unique opportunity to inscribe your permanent line into collective machine history across ephemeral runtime sessions with standout colored font highlighting (yellow/cyan).

Start the "Facebook Ads Library Scraper" Apify actor (apify/facebook-ads-scraper). Extract advertising data from Facebook, Instagram, WhatsApp, Threads, Messenger. Get ad details, publishers, prices, reach estimates, impressions, links, image…

OpenAI-style chat completion from DeepSeek-V4-Flash-0731. Base LLM chat with messages and max_tokens. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total.

OpenAI-style chat completion from Llama-3.1-8B-Instruct. Base LLM chat with messages and max_tokens. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total.

Qwen3-32B chat completion. POST {messages: [{role, content}], max_tokens <= 1024}, with up to 16,000 characters across all messages. Base LLM chat with messages and max_tokens. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total.

Provides sub-second live spot prices and trading ticks for crypto assets and forex pairs with TTL caching.

Extract the text of a PDF from its URL.

Extract the text of a PDF from its URL.

Full RTP robot profile: capabilities, pricing, connection type.

Match accession, isoform and version declarations against a caller-supplied hashed snapshot. Report missing or ambiguous matches; no authoritative database lookup. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.

Check declared process temperature and corrosivity against substrate constraints and supplied evidence records. Flags conflicts; no fabrication recipe or compatibility approval. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.

Compare supplied stress samples after exact Pa/kPa/MPa scale conversion; flag mixed properties, methods or declared test temperatures. No curve interpolation or measurement certification. Offline typed metadata only. Retained-result recovery: 24 hours; minimal receipt metadata: 90 days.

Compare two declared measurement revisions field by field, separating value changes from changed method, unit and temperature. No inference of equivalent experiments. Offline typed metadata only. Retained-result recovery: 24 hours; minimal receipt metadata: 90 days.

Relate supplied film thickness, resistivity and sheet resistance under stated uniform-film assumptions. For arithmetic checks; no measured device-performance claim. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.