# Reliability architecture

> LMU AI reliability architecture: multi-source routing, health probes, and three-tier automatic failover; 99.5% availability target on Standard and Enterprise.

URL: https://docs.lmuai.ai/docs/guide/reliability



We treat "stability" as the product's number-one feature. This page explains how we achieve that, and what happens when something goes wrong.

## Why is reliability so hard? [#why-is-reliability-so-hard]

Developers who connect directly to the official API run into things like:

* Regional rate limiting / unavailability
* A single payment channel or account getting banned
* Compatibility issues during model version switches
* Queuing at peak hours and spikes in first-token latency

If a relay service is just a simple proxy, these problems are **passed through as-is** to users, or even made worse. Our approach is to design the system on the premise that "upstreams are unstable," rather than treating that as an exception.

## Our multi-source routing architecture [#our-multi-source-routing-architecture]

For every API call, the request is handled along the following path:



**Core mechanisms:**

* **Multi-upstream pool**: multiple independent channels sit behind the same model, avoiding single points of failure
* **Health probing**: we continuously monitor each upstream's success rate, first-token latency, and rate-limit rate, and **unhealthy channels are automatically down-weighted or removed**
* **Automatic failover**: when the primary channel returns 5xx / rate limiting / timeouts, the request switches to a backup channel within milliseconds, **usually with no impact on your side**
* **Stream interruption reconnect**: when a streaming response drops midway, we attempt to resume it on protocols that support it

## Service level (SLA) [#service-level-sla]

Our external commitments are grounded in "what we can actually deliver" — we don't make empty promises.

| Tier       | Availability target | Monthly report | Business contract                           |
| ---------- | ------------------- | -------------- | ------------------------------------------- |
| Economy    | Best-effort         | —              | Not applicable                              |
| Standard   | 99.5%               | —              | Not applicable                              |
| Enterprise | 99.5%               | Provided       | Higher SLA and compensation terms available |

> The Economy tier is for individual developers who want the best value and can tolerate occasional fluctuations; if your business has hard reliability requirements, choose the Enterprise tier or contact our sales team for a custom plan.

How availability is measured:

* We count only the request success rate "on the LMU AI side," **excluding user-side network problems, parameter errors, and content refusals from the upstream model itself**
* A single failure lasting \< 60 seconds is not counted
* The monthly report includes success rates and P95 latency broken down by model and by time period

## What happens during an incident [#what-happens-during-an-incident]

**Brief jitter (\< 5 minutes)**

* The routing layer switches upstreams automatically, with no announcement
* The [status page](https://api.lmuai.ai/monitor) records the event

**A single upstream outage (\< 1 hour)**

* The routing layer completes the switch; if it's visible to some users/models, we post it on the status page
* Standard and Enterprise users are notified by email

**Regional or simultaneous multi-upstream impact**

* The event is pinned on the status page with periodic updates
* Enterprise users get progress updates by email in real time
* A postmortem is published within 48 hours after the event ends

## What we don't do [#what-we-dont-do]

To avoid misleading users, we currently do **not** promise the following:

* **Zero-latency, seamless switching**: failover introduces extra latency from milliseconds to seconds, so it will never be completely seamless
* **Cross-model compatibility compensation**: if an upstream model itself is retired (for example, a model version is discontinued by the provider), we announce it rather than silently switching to a different model
* **Unlimited retries**: failed requests are retried a limited number of times per policy, so you don't pay for unexpected repeat calls

## FAQ [#faq]

<Callout type="info" title="Why do I still hit failures occasionally?">
  No system is 100% available. Our goal is to keep overall availability above 99.5% and to recover quickly when failures occur. If you experience persistent failures (for example, the same kind of request failing multiple times within 5 minutes), please contact support with your request ID and we'll prioritize the investigation.
</Callout>

<Callout type="info" title="How do I apply for the Enterprise tier?">
  See the [Enterprise plans](/docs/enterprise) page, or contact sales directly:

  * Email: [business@lmuai.com](mailto:business@lmuai.com)
  * WeChat / phone: 18599001010
</Callout>