Zro (MoonMath)
Try Zro (MoonMath) on us. Starter credit covers your first requests, then one key reaches all 6 Zro (MoonMath) models, with the privacy posture shown on every route.
Zro (MoonMath)zro
MoonMath's OpenAI-compatible inference service for open models.
These privacy labels describe Zro (MoonMath), 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 | Zro (MoonMath) |
|---|---|
| API operator country | Not verified Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://zro.moonmath.ai/ |
| Models | 6 public models |
| Credits routes | 6 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| Policy note | Zro declares no retention of prompts, outputs or request bodies and no training or secondary use without separate consent, including by its infrastructure providers. Short-lived, account-scoped prompt caches and content-free operational metadata remain. This is provider-declared ZDR, not independently verified confidential compute or E2EE. Policy source |
Documentation and policy sources
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
- Europe (countries unspecified); United States
Provider-declared inference locations, including third-party capacity. Authentication is routed through the EU. - Can locations change?
- Inference is dynamically placed within the API key's allowed regions.
- Provider region pinning
- Provider supports per-key Europe/US region restrictions and fails closed outside them.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- Europe or United States; no fixed-country or per-request residency commitment on this route.
- Evidence
- Public provider API and privacy documentation. 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
17 samplesContinuously sampled across Zro (MoonMath)'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 | 1458 ms |
|---|---|
| Effective throughput | 184 tok/s n=2 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| zro/dolly2-security | 1213 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 1412 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4.1-flash | 1458 ms | — | 100.00% | — | 8 |
| z-ai/glm-5.3 | 1549 ms | 184 tok/s n=2 | 100.00% | — | 3 |
| zro/dolly1-security | 1817 ms | — | 100.00% | — | 3 |
| minimax/minimax-m3.1-flash | — | — | — | 4 provider_auth_config |
0 |
Zro (MoonMath) performance history · Full provider & model leaderboard.
Models served by Zro (MoonMath).
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#24 | 1,048,576 | $0.3165/1M | $0.01/1M | $1.266/1M |
minimax/minimax-m3.1-flashMiniMax: MiniMax M3.1 Flash |
IQ 120#49 | 1,048,576 | $0.15825/1M | $0.01266/1M | $0.633/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 124#30 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 119#50 | 1,048,576 | $0.15825/1M | $0.03165/1M | $0.5275/1M |
zro/dolly1-securityDolly 1 Security |
— | 1,000,000 | $0.47475/1M | $0.09495/1M | $1.5825/1M |
zro/dolly2-securityDolly 2 Security |
— | 1,000,000 | $2.2155/1M | $0.41145/1M | $6.963/1M |
Questions
Does Zro (MoonMath) have zero data retention?
TrustedRouter records Zro (MoonMath) as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Zro (MoonMath) end-to-end encrypted?
TrustedRouter does not currently mark Zro (MoonMath) 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 Zro (MoonMath) models are available through TrustedRouter?
This page currently lists 6 public Zro (MoonMath) models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.