● Early access opening soon

An LLM that doesn't make things up.

vanKonijnenburg is a large language model trained end-to-end for grounded answers. Evaluated against Google's official FACTS Grounding methodology on 643 independently fact-checked answers: 0 fabricated facts, only 4 with a reasoning error.

POST /v1/chat/completions { "model": "vankonijnenburg-1", "messages": [...] } { "choices": [...], "grounding_score": 0.99 }
Get early access →
~99%

estimated score under Google's official FACTS Grounding methodology, on our internal 643-answer fact-checking benchmark (checked claim-by-claim against source documents)

4 / 643

answers with a residual reasoning error — the only issues found; not one fabricated fact across the whole benchmark

Under our own stricter internal measure — which also counts reasoning errors and output artifacts, not just literal source-matching — the score is 95.3%. We report both rather than only the flattering one.

Why it doesn't hallucinate

Grounding is trained in, not bolted on afterward with a separate checking step.

1

Trained on real evidence

Every training example follows a Chain-of-Evidence: each claim traces back to a verifiable source, not just plausible-sounding text.

2

Tuned to reason, not guess

Direct Preference Optimization specifically targets the reasoning errors that generic LLM judges miss — scope mismatches, category errors, misapplied facts.

3

Independently verified

Every answer in our benchmark was checked claim-by-claim against its source document, by hand — not a single automated pass/fail score.

Pricing

Usage-based, like the LLM APIs you already integrate with.

Early access
Pay per message — exact pricing announced at launch

No monthly minimum. Waitlist members get preferential early pricing and priority onboarding.

Join the waitlist

vanKonijnenburg — the grounded LLM. We're onboarding a small group of early users first. Leave your details and we'll reach out.