AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

llm-analytics-setup

PostHog LLM analytics for all supported providers

Original source
posthog
License
MIT
Pinned revision
cac7c80a9e5b73484d18eda1bffb47297c938e0c

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read posthog--llm-analytics-setup at revision cac7c80a9e5b73484d18eda1bffb47297c938e0c, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 38

references/openrouter.md

OpenRouter LLM analytics installation - Docs

  1. 1

    Install the PostHog SDK

    Required

    Alternative: OpenRouter Broadcast

    OpenRouter also offers a native Broadcast feature that can automatically send LLM analytics data to PostHog without requiring SDK instrumentation. This is a simpler option if you don't need the additional customization that our SDK provides.

    Setting up analytics starts with installing the PostHog SDK for your language. LLM analytics works best with our Python and Node SDKs.

    PostHog AI

    Python

    pip install posthog
    

    Node

    npm install @posthog/ai posthog-node
    
  2. 2

    Install the OpenAI SDK

    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

    Python

    pip install openai
    

    Node

    npm install openai
    
  3. 3

    Initialize PostHog and OpenAI client

    Required

    We call OpenRouter through the OpenAI client and generate a response. We'll use PostHog's OpenAI provider to capture all the details of the call. Initialize PostHog with your PostHog project token and host from your project settings, then pass the PostHog client along with the OpenRouter config (the base URL and API key) to our OpenAI wrapper.

    PostHog AI

    Python

    from posthog.ai.openai import OpenAI
    from posthog import Posthog
    posthog = Posthog(
        "<ph_project_token>",
        host="https://us.i.posthog.com"
    )
    client = OpenAI(
        base_url="https://openrouter.ai/api/v1",
        api_key="<openrouter_api_key>",
        posthog_client=posthog  # This is an optional parameter. If it is not provided, a default client will be used.
    )
    

    Node

    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({
      baseURL: 'https://openrouter.ai/api/v1',
      apiKey: '<openrouter_api_key>',
      posthog: phClient,
    });
    // ... your code here ...
    // IMPORTANT: Shutdown the client when you're done to ensure all events are sent
    phClient.shutdown()
    

    Note: This also works with the AsyncOpenAI client.

    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 for more details.

  4. 4

    Call OpenRouter

    Required

    Now, when you call OpenRouter with the OpenAI SDK, PostHog automatically captures an $ai_generation event. You can also capture or modify additional properties with the distinct ID, trace ID, properties, groups, and privacy mode parameters.

    PostHog AI

    Python

    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.choices[0].message.content)
    

    Node

    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: "company_id_in_your_db" }, // optional
        posthogPrivacyMode: false // optional
    });
    console.log(completion.choices[0].message.content)
    

    Notes:

    • We also support the old chat.completions API.
    • 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 to learn more.

    You can expect captured $ai_generation events to have the following properties:

    | Property | Description | | --- | --- | | $ai_model | The specific model, like gpt-5-mini or claude-4-sonnet | | $ai_latency | The latency of the LLM call in seconds | | $ai_time_to_first_token | Time to first token in seconds (streaming only) | | $ai_tools | Tools and functions available to the LLM | | $ai_input | List of messages sent to the LLM | | $ai_input_tokens | The number of tokens in the input (often found in response.usage) | | $ai_output_choices | List of response choices from the LLM | | $ai_output_tokens | The number of tokens in the output (often found in response.usage) | | $ai_total_cost_usd | The total cost in USD (input + output) | | [...] | See full list of properties |

  5. Verify traces and generations

    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.

    LLM generations in PostHogLLM generations in PostHog

    Check for LLM events in PostHog

  6. 5

    Next steps

    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 | Learn the basics of how LLM calls become events in PostHog. | | Generations | Read about the $ai_generation event and its properties. | | Traces | Explore the trace hierarchy and how to use it to debug LLM calls. | | Spans | Review spans and their role in representing individual operations. | | Anaylze LLM performance | Learn how to create dashboards to analyze LLM performance. |

Community questions

Ask a question

Was this page useful?

HelpfulCould be better