Neurometric AI
Try Neurometric AI on us. Starter credit covers your first requests, then one key reaches all 7 Neurometric AI models, with the privacy posture shown on every route.
Neurometric AIneurometric
These privacy labels describe Neurometric AI, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Neurometric AI |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.neurometric.ai/ |
| Models | 7 public models |
| Credits routes | 7 |
| Zero data retention | no |
| Verified confidential inference | Not verified |
| Policy note | Neurometric states that TrustedRouter requests run with upstream trace logging disabled: prompts and completions are not written to observability or object storage, and only aggregate request counts and token totals are retained. This is classified as no-store, not contractual ZDR or confidential compute. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- United States (AWS us-west-2)
Neurometric supplied AWS us-west-2 in its marketplace application. New models and exhaustive failover locations need separate confirmation. - Can locations change?
- Model-specific placement and failover changes require provider confirmation.
- Provider region pinning
- No per-request regional pin verified.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- AWS us-west-2, provider-submitted hosting declaration; not a per-request receipt.
- Evidence
- Provider-submitted marketplace information. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
26 samplesContinuously sampled across Neurometric AI's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1387 ms |
|---|---|
| Effective throughput | — |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| neurometric/tool-choice | 815 ms | — | 100.00% | — | 6 |
| ibm-granite/granite-4.1-8b | 870 ms | — | 100.00% | — | 2 |
| neurometric/classification-router | 966 ms | — | 100.00% | — | 4 |
| neurometric/grounded-document-qa | 1387 ms | — | 100.00% | — | 5 |
| google/gemma-4-12b-it | 2004 ms | — | 100.00% | — | 3 |
| neurometric/conversation-summary | 2033 ms | — | 100.00% | — | 3 |
| neurometric/document-structured-extraction | 2360 ms | — | 100.00% | — | 3 |
Neurometric AI performance history · Full provider & model leaderboard.
Models served by Neurometric AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
google/gemma-4-12b-itgoogle/gemma-4-12B-it |
IQ 94#150 | 0 | $0.01055/1M | Not published | $0.1266/1M |
ibm-granite/granite-4.1-8bgranite-4.1-8b |
— | 32,768 | $0.05275/1M | Not published | $0.1055/1M |
neurometric/classification-routerClassification Router |
— | 32,768 | $0.01055/1M | Not published | $0.1055/1M |
neurometric/conversation-summaryConversation Summary |
— | 49,152 | $0.01055/1M | Not published | $0.1055/1M |
neurometric/document-structured-extractionDocument Structured Extraction |
— | 49,152 | $0.01055/1M | Not published | $0.1055/1M |
neurometric/grounded-document-qaGrounded Document QA |
— | 49,152 | $0.01055/1M | Not published | $0.1055/1M |
neurometric/tool-choicetool-choice |
— | 32,768 | $0.01055/1M | Not published | $0.1055/1M |
Questions
Does Neurometric AI have zero data retention?
TrustedRouter does not currently mark Neurometric AI as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Neurometric AI end-to-end encrypted?
TrustedRouter does not currently mark Neurometric AI as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Neurometric AI models are available through TrustedRouter?
This page currently lists 7 public Neurometric AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.