MaxModel

LLM answers grounded in your own sources — with verbatim citations and hallucinations removed.

MaxModel is the developer layer of the maxmodel.com gateway. Same key, same OpenAI-compatible API, one new capability: verified output. You pass your own sources (docs, wiki pages, retrieved RAG chunks); the API returns the model’s answer with verbatim citations and a list of any claim it could not ground — stripped out before it ever reaches your users.

npm i maxmodel

Why it’s different

Most “citation” features ask one model to grade another model’s answer. That can hallucinate too.

MaxModel’s grounding check is deterministic code, not an LLM judge: every cited quote must appear character-for-character in the source you supplied, or it is dropped. No quote, no claim.

import { MaxModel } from 'maxmodel'
 
const mx = new MaxModel({ apiKey: process.env.MAXMODEL_KEY! })
 
const out = await mx.verified.create({
  model: 'gpt-5.5-pro',
  messages: [{ role: 'user', content: 'What is our refund policy?' }],
  sources: [
    { id: 'refunds.md', text: 'Full refunds within 30 days. No refunds after 30 days.' },
  ],
})
 
console.log(out.text)
// "Full refunds are available within 30 days [refunds.md]. ..."
out.citations   // each quote is a verbatim substring of refunds.md
out.unsupported // claims that could not be grounded — caught, not shipped

Where to go next

Quickstart — install and make your first verified call in two minutes.
verified.create — full parameter and response reference.
How verification works — the deterministic moat, explained honestly.
Errors — typed errors and the HTTP table.
Migrating from OpenAI — change the import, add sources.

What MaxModel is not (v1)

It does not retrieve for you — you pass the sources (post-retrieval chunks).
/v1/verified is non-streaming: verification needs the full claim set before it can answer.
No GUI. It’s an SDK + API for developers.

Quickstart