sebbi.pro
GATEWAY · ONE LINE

Change one line.
Govern every AI call.

Point your app's OpenAI or Anthropic base URL at sebbi.pro. Every call is scored before it leaves, stopped if it should be, sealed into the chain, and answered with a receipt anyone can check against Bitcoin. No SDK. No integration project. Your provider key passes straight through.

1 · Get your gateway URL

Paste your sebbi.pro API key. No key yet? Get one free. Your first 1,000 gateway calls are free; then add a card — 50p per device a month. Want us to set it all up? Governed in 7 days — £495.

2 · Change one line


Prefer to keep the URL clean? Use https://sebbi.pro/g/openai/v1 and send your sebbi.pro key in an X-Sebbi-Key header instead.

3 · Every answer carries a receipt

Each response comes back with one standard header. Anyone can check the decision against Bitcoin.

AI-Decision-Receipt: v=1, issuer="sebbi.pro", decision=ALLOW, score=0.12,
  block=1042, seal="9f2c…", req="<sha256 of your request>", call="GC-7Q2M9X4KDP",
  verify="https://sebbi.pro/forever?block=1042"

The request and response fingerprints are timestamped in Bitcoin too, so you can later prove exactly what was asked and exactly what the AI answered. The open standard →

What happens to each call

01 · FINGERPRINT

The request is hashed. The prompt itself is never stored.

02 · DECIDE

The engine scores it ALLOW, CHALLENGE or BLOCK in milliseconds and seals the decision.

03 · GATE

BLOCK stops here — the provider is never called. ALLOW streams straight through, token by token.

04 · PROVE

Request and response fingerprints go into Bitcoin. The receipt header ties it all together.

Optional headers: X-Sebbi-User (who the call is for — also the billing meter unless you send a device), X-Sebbi-Device (billing meter), X-Sebbi-Country, X-Sebbi-Pack (your Signal Pack), X-Sebbi-On-Challenge: block (hold CHALLENGE calls).

AI news
TechCrunchHealthleap raises $38M for its AI that flags hospital patients who may need a closer look27mTechCrunchTony Fadell on why the first wave of AI gadgets failed — and what comes next53mTechCrunchGoogle experiments with an AI-powered gaming platform58mTechCrunchOpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots1hArs TechnicaMistral says "Le Chonk" can challenge the best AI models1hArs TechnicaGoogle rolls out improved SynthID AI content detector, now available globally1hTechCrunchGoogle’s new SynthID website can identify AI-generated media1hThe VergeAI could upend food delivery3hWiredOpenAI Wants Its New Agent to Run Your Life. Mine Said It Loved Me4hThe VergeChatGPT for Teens is an ‘unacceptable risk,’ says Common Sense Media6hThe VergeOpenAI drops another batch of mathematical breakthroughs16hArs TechnicaOpenAI will watermark ChatGPT outputs by default—but only in the EU18hWired‘Artificial’ Roasts AI’s Creators—and Sends a Dark Warning About Its Dangers20hWiredOpenAI Is Pissing Off a Bunch of Mathematicians—Again22hThe VergeGoogle is about to remove free access to Gemini Flash and Pro1dWiredMistral Says Its New AI Model ‘Le Chonk’ Is the Best Open-Weight Offering Outside of China1dArs TechnicaOpenAI agents tried to hack Wikipedia tools and flooded it with traffic1dBBC NewsItalian PM files to trademark her voice against AI threats1dWiredKevin Roose Didn’t Use AI to Write His Book About AI1dThe VergeGemini Call for Me might tell your mom you’re running late1dBBC NewsPentagon stops using Anthropic AI tools after blacklisting company, BBC told1dMIT Technology ReviewConnecting AI agents to enterprise knowledge1dArs TechnicaAI glasses face their first major government crackdown2dMIT Technology ReviewBringing predictive analytics to the agentic AI era2dTechCrunchHealthleap raises $38M for its AI that flags hospital patients who may need a closer look27mTechCrunchTony Fadell on why the first wave of AI gadgets failed — and what comes next53mTechCrunchGoogle experiments with an AI-powered gaming platform58mTechCrunchOpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots1hArs TechnicaMistral says "Le Chonk" can challenge the best AI models1hArs TechnicaGoogle rolls out improved SynthID AI content detector, now available globally1hTechCrunchGoogle’s new SynthID website can identify AI-generated media1hThe VergeAI could upend food delivery3hWiredOpenAI Wants Its New Agent to Run Your Life. Mine Said It Loved Me4hThe VergeChatGPT for Teens is an ‘unacceptable risk,’ says Common Sense Media6hThe VergeOpenAI drops another batch of mathematical breakthroughs16hArs TechnicaOpenAI will watermark ChatGPT outputs by default—but only in the EU18hWired‘Artificial’ Roasts AI’s Creators—and Sends a Dark Warning About Its Dangers20hWiredOpenAI Is Pissing Off a Bunch of Mathematicians—Again22hThe VergeGoogle is about to remove free access to Gemini Flash and Pro1dWiredMistral Says Its New AI Model ‘Le Chonk’ Is the Best Open-Weight Offering Outside of China1dArs TechnicaOpenAI agents tried to hack Wikipedia tools and flooded it with traffic1dBBC NewsItalian PM files to trademark her voice against AI threats1dWiredKevin Roose Didn’t Use AI to Write His Book About AI1dThe VergeGemini Call for Me might tell your mom you’re running late1dBBC NewsPentagon stops using Anthropic AI tools after blacklisting company, BBC told1dMIT Technology ReviewConnecting AI agents to enterprise knowledge1dArs TechnicaAI glasses face their first major government crackdown2dMIT Technology ReviewBringing predictive analytics to the agentic AI era2d