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

# PostHog

Connect your OpenStack proxy to [PostHog](https://posthog.com) to automatically capture rich [LLM analytics](https://posthog.com/docs/llm-analytics) — no PostHog SDK or client-side changes required.

## How it works

* OpenStack emits a `$ai_generation` server-side event after every routed request.
* The distinct ID is resolved from the provided user id, so make sure you pass a stable user identifier such as the `X-Openstack-User` header.
* Events include latency, token usage, cost breakdowns, request / response metadata, and error flags drawn from the proxy state.

Events are recorded even if the upstream model call fails, enabling funnel and reliability analysis.

## Setup

1. In the OpenStack dashboard, open the paywall you want to analyse.
2. Navigate to **Configuration → Analytics** and enable the PostHog toggle.
3. Paste your PostHog `Project API Key`, and add a `Project ID` to annotate events.
4. Save configuration. No code changes are required in your app.

<Info>
  This is especially helpful for low-code and no-code stacks (Zapier, n8n, Bubble, Make) where you cannot easily install
  PostHog libraries.
</Info>

## Event payload

Each `$ai_generation` event contains the consolidated proxy context. Key properties include:

| Property                                | Description                                                                             |
| --------------------------------------- | --------------------------------------------------------------------------------------- |
| `$ai_model`                             | Model name recorded by the upstream provider.                                           |
| `$ai_provider`                          | Detected provider (`openai`, `anthropic`, `gemini`, `openrouter`, etc.).                |
| `$ai_input`                             | Sanitized request messages captured by OpenStack (tools removed when privacy requires). |
| `$ai_output_choices`                    | Sanitized assistant outputs or tool deltas when available.                              |
| `$ai_input_tokens`, `$ai_output_tokens` | Token counts (prompt / completion) from provider usage metadata.                        |
| `$ai_latency`                           | Total provider latency in seconds.                                                      |
| `$ai_http_status`                       | Upstream HTTP status or proxy error code.                                               |
| `$ai_is_error`, `$ai_error`             | Flags and messages for failed generations.                                              |
| `$ai_total_cost_usd`                    | Request cost in USD.                                                                    |

## Building dashboards

* Use the `$ai_is_error` flag to build error funnels and monitor vendor reliability.
* Segment by `$ai_model`, or `$ai_provider` to understand usage patterns.
* Combine with PostHog notebooks or dashboards to compare LLM costs versus revenue, and trigger alerts when latency spikes.

<Note>
  Make sure every request to OpenStack includes a stable `user` value. Without it, events are dropped because PostHog
  requires a distinct ID for analytics.
</Note>

## Related resources

* [PostHog API reference](https://posthog.com/docs/llm-analytics/manual-capture) — learn how `$ai_generation` events are captured.