Capturing large AI events

AI events can get big – a single generation can carry megabytes of prompt context or base64-encoded media, more than regular event capture accepts. To handle this, PostHog sends AI events like $ai_generation and $ai_embedding through a dedicated ingestion path that accepts events up to 8MB.

During the beta, this path is opt-in. How you opt in depends on how you capture AI events today.

Using the SDK integrations

By default, our SDK integrations redact base64 media and may truncate very long strings before capture. To capture everything in full, pass a single flag when creating your PostHog client:

from posthog import Posthog

posthog = Posthog(
    "<ph_project_api_key>",
    host="https://us.i.posthog.com",
    enable_full_ai_capture=True
)

const posthog = new PostHog(
  '<ph_project_api_key>',
  {
    host: 'https://us.i.posthog.com',
    enableFullAiCapture: true
  }
)

With the flag on, nothing is truncated or redacted. The one exception is privacy mode: when it's enabled, input and output content is still stripped, flag or no flag.

Calling capture_ai directly

If you build AI events yourself instead of using the integrations, call capture_ai (Python) or captureAi (Node) instead of capture. It takes the same arguments as capture and returns the captured event's UUID.

from posthog import Posthog

posthog = Posthog("<ph_project_api_key>", host="https://us.i.posthog.com")

uuid = posthog.capture_ai(
    "$ai_generation",
    distinct_id="user_123",
    properties={
        "$ai_trace_id": trace_id,
        "$ai_model": "gpt-5",
        "$ai_input": messages,
        "$ai_output_choices": choices,
    },
)

import { PostHog } from 'posthog-node'

const posthog = new PostHog('<ph_project_api_key>', { host: 'https://us.i.posthog.com' })

const uuid = posthog.captureAi({
  distinctId: 'user_123',
  event: '$ai_generation',
  properties: {
    $ai_trace_id: traceId,
    $ai_model: 'gpt-5',
    $ai_input: messages,
    $ai_output_choices: choices,
  },
})

Send content as your provider produced it, including base64 and data URIs – there's no need to reshape payloads. capture_ai captures exactly what you pass it, without truncating or redacting anything. Privacy mode doesn't apply here, so leave out any content you don't want stored.

In serverless and other short-lived environments, use the awaitable variant in Node so the event is delivered before the runtime exits:

await posthog.captureAiImmediate({ distinctId: 'user_123', event: '$ai_generation', properties })

In Python, call posthog.flush() before exit (or enable sync_mode), just like with capture.

Other platforms

Not on Python or Node? Build events with manual capture and point your capture requests at the dedicated AI endpoint instead of the regular one – same request format, different path:

POST https://us.i.posthog.com/i/v0/ai/batch/

Limits

Events up to 8MB are accepted for now. The SDKs drop larger events before sending and log an error instead. The limit will increase as the beta continues.