> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pyai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Reliability, latency & regions

> PyAI's status page, uptime targets and contractual SLA path, expected realtime latency, single-region topology and data residency, and reconnect guidance.

What to expect operationally, and where to watch live health.

## Status & incidents

* **Status page:** [status.pyai.com](https://status.pyai.com), live surface
  health plus posted incidents and maintenance.
* **Subscribe:** machine feeds at `/incidents.json`, `/history.json`, and Atom
  `/feed.xml`; or get email updates (double opt-in) via
  `POST https://api.pyai.com/v1/status/subscribe`.
* During an incident, the status page is the source of truth for scope, impact,
  and updates.

## Uptime targets & SLA

PyAI runs to these **operational availability targets**:

| Surface                                      | Target     |
| -------------------------------------------- | ---------- |
| REST / control plane                         | **99.9%**  |
| Edge authentication                          | **99.95%** |
| Realtime voice (Omni / Cue / Hear streaming) | **99.5%**  |

<Note>
  These are **operational targets**, not a contractual commitment by themselves. A
  **contractual SLA** (with credits) is available on enterprise agreements, talk
  to us. Today PyAI runs a **single region**; higher availability tiers ride the
  multi-region program on the roadmap.
</Note>

## Latency

* **Omni (English), in-region:** about **390 ms median** turn-taking, measured
  from utterance-end to the first agent-audio frame.
* **Cue + your stack:** PyAI owns the speech-to-text leg only; your LLM, your TTS,
  and playback add to the end-to-end number, so budget for those on top of Cue's
  STT latency.

<Warning>
  **Serving region.** PyAI is served from a **single US region** today, there is
  **no India/APAC edge yet**. Callers far from the US will see cross-region
  round-trip added to every turn. If low latency in India is critical to your
  launch, raise it with us early; an India/APAC edge is roadmap, not available
  today.
</Warning>

## Regions & data residency

The platform runs in one US region. There is **no India (DPDP) data-residency
option today**. Mitigations that exist now: streaming Hear/Cue and Omni live
audio are **relayed, not persisted**; recordings are **off by default**; and
stored artifacts have bounded [retention](/security-and-data#data-retention). For
formal residency requirements, contact us, it's an enterprise/roadmap
conversation.

## Reconnect & retry

There is **no mid-call session resume**: a dropped realtime socket ends the
session, and reconnecting starts a **new** one (for Omni, re-send `configure`).
Recommended handling:

* Retry on `1011` (transient engine) and `4429` (over-cap) with exponential
  backoff; do **not** retry `4401` / `4403`, fix the key/scope first.
* Keep per-call state (your `session_label`, persona/context, a short running
  summary) in **your** backend so a reconnect can re-prime the session and
  continue gracefully.

See the [Omni protocol reference](/realtime/omni-protocol) for the full
close-code table and reconnect semantics.

## See also

<CardGroup cols={2}>
  <Card title="Errors & limits" href="/errors-and-limits">Error codes, rate, and concurrency limits.</Card>
  <Card title="Security & data" href="/security-and-data">Tenancy, retention windows, and recordings.</Card>
  <Card title="Omni wire protocol" href="/realtime/omni-protocol">Close codes and reconnect semantics.</Card>
  <Card title="Pricing & metering" href="/pricing-and-metering">Per-second billing and reconciliation.</Card>
</CardGroup>