AI Inference

Search products across China B2B wholesale marketplaces (Yiwugo, Made-in-China, DHgate) via a stealth browser farm. Returns structured products: title, price, MOQ, suppl…

Call when an agent needs a heuristic token count for text using chars4 (characters/4), words, or regex. Use it to budget a prompt before calling a model. Not a model tok…

Call when an agent needs broken JSON repaired deterministically (markdown fences, smart quotes, trailing commas, single quotes, unquoted keys), plus the transforms appli…

Substantive llms.txt repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold,…

Substantive llms.txt decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, ver…

Substantive llms.txt audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdic…

Basic company lookup (research_company). Give a company name and/or domain; returns the company name, Wikipedia summary and link, and the public homepage title, meta des…

Enriched prospect record (enrich_prospect). Company summary and domain plus contact details found on the company's public homepage (emails_found_on_page, phones_found_on…

Resolve a company name, website domain, registry number, LEI or VAT number to its official legal entity: registry, registry number, legal form, status, address, industry…

Private pay-per-call LLM inference for autonomous agents. Prompts run on our own GPU (house Qwen3 brain, resident model qwen3-14b); settled in USDC on Base L2.

Ask an LLM anything

For JavaScript-rendered pages & pages blocking native Minifetch that obeys robots.txt:…

minifetch.com

For JavaScript-rendered pages & pages blocking native Minifetch that obeys robots.txt: fetch thru external rotating proxy, render JS in headless browser & extract same c…

Generate text or JSON completions for one to 20 independent tasks. Choose GPT-6 Luna or GPT-6.1 Sol, or let task-based rules select each model. Review the selected model…

SingIt Ask: Ask a language model without an API key: any model listed at GET /v1/models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen and more; default deepseek-v4.1-flash)…

Mail and DNS hygiene of a domain over DNS over HTTPS: A, AAAA, MX, NS, TXT and CAA records; SPF parsed (mechanisms, the all qualifier, a lookup estimate, a warning above…

Clinical trial lookup against the full ClinicalTrials.gov registry: exact lookup by NCT number, or search by condition, intervention, or lead sponsor. Returns compact tr…

LLM inference over x402: POST a prompt (JSON body), get raw model output. Flat $0.05 per call (or metered pay-actual-usage when the upto scheme is on); every response pr…

Get tokens that moved significantly during off-hours (midnight to 8am UTC) with AI-generated analysis of what happened while you slept.

AI-generated executive summary of current market trends, top narratives, and notable momentum shifts.

Fundamentals engine for the HYPE token (Hyperliquid): live price, funding and open interest, fees and buyback flywheel, P/S valuation percentile, perp market share, unlo…

Grade any physical Pokémon, Magic: The Gathering, Yu-Gi-Oh, or Digimon trading card using a 3-stage AI pipeline: (1) Qwen Vision LLM analyzes corners, edges, and surface…

Council-tax challenge letter preview — verdict (letter_supportable / blocked-on-risk-ack / not-supportable) from the same neighbor-band cluster + statutory-route engine…

UK council-tax banding challenge check — neighbor-band cluster analysis against the free official VOA/SAA lookups, statutory route selection (formal proposal vs informal…

Flight compensation eligibility across 7 regimes — EU261, UK261, Canada APPR (incl. s.20 denied boarding), Brazil ANAC 400, Turkey SHY, India DGCA, Israel ASL — plus Mon…