AI Inference

Proof-of-Model: detect silent model substitution at any OpenAI-compatible inference endpoint. mode=fingerprint records what a seller serves today; mode=verify re-probes…

Security audit of code snippet (SQLi, XSS, auth bypass, secret leaks, unsafe deserialization).

Agent-readiness audit of any public URL: score /100 with per-check raw evidence, published weights, and a recompute recipe. Deterministic — no model, same input gives th…

Structured code review: correctness, security, edge cases, reuse. Returns numbered findings.

Multi-step reasoning and planning, served by Qwen3.8-27B abliterated (Heretic) on a local RTX 5090 via vLLM.

Generate tests for a code snippet (matches file's existing test framework).

Refactor code while preserving behavior. Returns diff + rationale.

Uncensored coder completions, served by Qwen3.8-27B abliterated (Heretic) on a local RTX 5090 via vLLM.

Build a regex from a natural-language description. Returns just the regex + one test string.

Uncensored general chat (Qwen3.8-27B Heretic).

Single-call business scrape for one domain: business name with its extraction source, published contact surface, detected technology platforms with per-detection evidenc…

Fetch a public web page and return its main content as clean Markdown with title, byline and metadata. Ideal input for LLM agents, RAG and summarization.

Fetch one public web page and return its title and clean Markdown (headings, links, lists, code, tables). Honors robots.txt, SSRF-guarded, HTML only, 1 MB / 5 s caps. No…

Trading decision for a crypto asset or stock ($1): every dataset (order flow, technicals, smart money, SEC fundamentals, insiders, perp positioning, market risk, news) a…

Trading decision for a crypto asset or stock ($1): every dataset (order flow, technicals, smart money, SEC fundamentals, insiders, perp positioning, market risk, news) a…

Fix broken JSON (trailing commas, single quotes, unquoted keys). Returns only valid JSON.

Explain a regex in plain English. Paste the regex in message content.

Convert a curl command to Python/JS/Go. Specify target language in the message.

Explain a SQL query in plain English. Paste query in message.

Estimate how many tokens a text consumes for each major model family (GPT, Claude, Gemini, Llama, DeepSeek) using a character/word heuristic that is within ~10% of real…

Calculate the API cost of an LLM call: input and output tokens × published per-million prices for 15 current models (OpenAI, Anthropic, Google, DeepSeek, xAI, Meta). Bat…

Parse natural-language date and time expressions — "in two weeks", "next friday at 3pm", "dec 25th" — into exact ISO 8601 dates. Deterministic parsing (no LLM guessing);…

Fetch a web page server-side and convert it to clean markdown — headings, links, lists, tables and text, with scripts, styles and boilerplate stripped. The 'reader' patt…

Geolocate an IP: city, region, country, ASN/org, and timezone, from a cached keyless public geolocation feed (no LLM, no GPU). Call with ?ip=<ip>, or bare to geolocate y…