Free to start

Grounded Document QA

Try Grounded Document QA on us. Starter credit covers your first requests, then one key reaches this route and every other model in the catalog.

`neurometric/grounded-document-qa`

US providers Neurometric AI

All models

Publisher	Neurometric AIneurometric
AI IQ	No AI IQ profile matched yet.
Context	49,152 tokens
Providers	Neurometric AI
Credits routes	1 provider route
Modes	chat US providers
Billing	Credits

How to use Grounded Document QA

Answers questions only from supplied document chunks, cites the supporting chunk, and abstains when the answer is not present.

Input	Put one JSON object in the user message with an optional request_id, a chunks array, and question. Each chunk needs a stable id, text, and status. Mark current sources authoritative and outdated sources superseded. The model will not use outside knowledge.
Output	Returns only JSON with answer and citations. answer is the shortest exact supporting text span or null when the documents do not contain the answer. citations contains only supporting chunk IDs and is empty when answer is null.

Example input

{
    "chunks": [
      {
        "id": "DOC-1",
        "status": "authoritative",
        "text": "The Acme renewal date is October 15, 2026."
      }
    ],
    "question": "What is the Acme renewal date?"
  }

Example output

{
    "answer": "October 15, 2026",
    "citations": ["DOC-1"]
  }

Current route evidence

Live leaderboard

$0.01055/1MLowest Credits input price

$0.1055/1MLowest Credits output price

not enough dataFastest measured p50 TTFT

not enough dataHighest measured throughput

Recent provider-route uptime spans not enough data across 1 route and 1 provider. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.

Provider	Input	Cached input	Output	Weight format	TR router attested	Provider policy
Neurometric AIneurometric	$0.01055/1M	Not published	$0.1055/1M	Unknown	yes	no verified privacy claim

Compare Grounded Document QA

All comparisons

MoonshotAI: Kimi K3 vs Grounded Document QA29 combined provider routes

Questions

What model ID should I use for Grounded Document QA?

Use neurometric/grounded-document-qa as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve Grounded Document QA?

TrustedRouter currently lists Neurometric AI for Grounded Document QA. Provider availability and routing eligibility can change as catalog and health data update.

How much does Grounded Document QA cost through TrustedRouter?

The current lowest Credits input price is $0.01055/1M and the lowest Credits output price is $0.1055/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Grounded Document QA?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.