Chapter 150 · LLM Analytics Setup
Subchapter 150.27
references/openai.mdMarkdown6 KBView on GitHub
Required
Setting up analytics starts with installing the PostHog SDK for your language. LLM analytics works best with our Python and Node SDKs.
PostHog AI
pip install posthognpm install @posthog/ai posthog-node2
Required
Install the OpenAI SDK. The PostHog SDK instruments your LLM calls by wrapping the OpenAI client. The PostHog SDK does not proxy your calls.
PostHog AI
pip install openainpm install openai3
Required
Initialize PostHog with your project token and host from your project settings (opens in a new tab), then pass it to our OpenAI wrapper.
PostHog AI
from posthog.ai.openai import OpenAI
from posthog import Posthog
posthog = Posthog(
"<ph_project_token>",
host="https://us.i.posthog.com"
)
client = OpenAI(
api_key="your_openai_api_key",
posthog_client=posthog # This is an optional parameter. If it is not provided, a default client will be used.
)import { OpenAI } from '@posthog/ai'
import { PostHog } from 'posthog-node'
const phClient = new PostHog(
'<ph_project_token>',
{ host: 'https://us.i.posthog.com' }
);
const openai = new OpenAI({
apiKey: 'your_openai_api_key',
posthog: phClient,
});
Note: This also works with the
AsyncOpenAIclient.
Proxy note
These SDKs do not proxy your calls. They only fire off an async call to PostHog in the background to send the data. You can also use LLM analytics with other SDKs or our API, but you will need to capture the data in the right format. See the schema in the manual capture section (opens in a new tab) for more details.
4
Required
Now, when you use the OpenAI SDK to call LLMs, PostHog automatically captures an $ai_generation event. You can enrich the event with additional data such as the trace ID, distinct ID, custom properties, groups, and privacy mode options.
PostHog AI
response = client.responses.create(
model="gpt-5-mini",
input=[
{"role": "user", "content": "Tell me a fun fact about hedgehogs"}
],
posthog_distinct_id="user_123", # optional
posthog_trace_id="trace_123", # optional
posthog_properties={"conversation_id": "abc123", "paid": True}, # optional
posthog_groups={"company": "company_id_in_your_db"}, # optional
posthog_privacy_mode=False # optional
)
print(response.output_text)const completion = await openai.responses.create({
model: "gpt-5-mini",
input: [{ role: "user", content: "Tell me a fun fact about hedgehogs" }],
posthogDistinctId: "user_123", // optional
posthogTraceId: "trace_123", // optional
posthogProperties: { conversation_id: "abc123", paid: true }, // optional
posthogGroups: { company:
Notes:
- We also support the old
chat.completionsAPI.- This works with responses where
stream=True.- If you want to capture LLM events anonymously, don’t pass a distinct ID to the request.
See our docs on anonymous vs identified events (opens in a new tab) to learn more.
You can expect captured $ai_generation events to have the following properties:
5
Optional
PostHog can also capture embedding generations as $ai_embedding events. Just make sure to use the same posthog.ai.openai client to do so:
response = client.embeddings.create(
input="The quick brown fox",
model="text-embedding-3-small",
posthog_distinct_id="user_123", # optional
posthog_trace_id="trace_123", # optional
posthog_properties={"key": "value"} # optional
posthog_groups={"company": "company_id_in_your_db"} # optional
posthog_privacy_mode=False # optional
)Recommended
Confirm LLM events are being sent to PostHog
Let’s make sure LLM events are being captured and sent to PostHog. Under LLM analytics, you should see rows of data appear in the Traces and Generations tabs.


6
Recommended
Now that you’re capturing AI conversations, continue with the resources below to learn what else LLM Analytics enables within the PostHog platform.
| Resource | Description |
|---|---|
| Basics (opens in a new tab) | Learn the basics of how LLM calls become events in PostHog. |
| Generations (opens in a new tab) | Read about the $ai_generation event and its properties. |
| Traces (opens in a new tab) | Explore the trace hierarchy and how to use it to debug LLM calls. |
| Spans (opens in a new tab) | Review spans and their role in representing individual operations. |
| Anaylze LLM performance (opens in a new tab) | Learn how to create dashboards to analyze LLM performance. |
Ask a question
HelpfulCould be better