Classification Router
Compare every TrustedRouter route for Classification Router, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.
neurometric/classification-router
| Publisher | Neurometric AIneurometric |
|---|---|
| AI IQ | No AI IQ profile matched yet. |
| Context | 32,768 tokens |
| Providers | |
| Credits routes | 1 provider route |
| Modes | chat US providers |
| Billing | Credits |
How to use Classification Router
Classifies one or more requests against a caller-defined taxonomy and uses an explicit fallback when no supplied label applies.
| Input | Put one JSON object in the user message with taxonomy_id, labels, fallback_label, and requests. labels maps each allowed label to its meaning. requests is an array of objects containing id and text. Every request ID is classified exactly once. |
|---|---|
| Output | Returns only one JSON object mapping each supplied request ID to exactly one supplied label. No labels outside the taxonomy are generated. The fallback label is used only when no described category applies. |
Example input
{
"taxonomy_id": "support",
"labels": {
"Billing": "Charges, payments, or refunds",
"Technical": "Errors, outages, or product malfunctions",
"Other": "No other label applies"
},
"fallback_label": "Other",
"requests": [
{
"id": "REQ-1",
"text": "Please refund this duplicate charge."
},
{
"id": "REQ-2",
"text": "The API returns a 502 error."
},
{
"id": "REQ-3",
"text": "What is your office address?"
}
]
}Example output
{
"REQ-1": "Billing",
"REQ-2": "Technical",
"REQ-3": "Other"
}Current route evidence
Live leaderboardRecent 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 | TR router attested | Provider policy |
|---|---|---|---|---|---|
| Neurometric AIneurometric | $0.01055/1M | Not published | $0.1055/1M | yes | no verified privacy claim |
Endpoint JSON: https://api.trustedrouter.com/v1/models/neurometric/classification-router/endpoints
Compare Classification Router
All comparisons- MoonshotAI: Kimi K2.6 vs Classification Router21 combined provider routes
Questions
What model ID should I use for Classification Router?
Use neurometric/classification-router as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Which providers serve Classification Router?
TrustedRouter currently lists Neurometric AI for Classification Router. Provider availability and routing eligibility can change as catalog and health data update.
How much does Classification Router 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 Classification Router?
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.