references/vercel-ai.md
Vercel AI SDK LLM analytics installation - Docs
-
1
Install dependencies
Required
Install the PostHog AI package, the Vercel AI SDK, and the OpenTelemetry SDK.
npm install @posthog/ai @ai-sdk/openai ai @opentelemetry/sdk-node @opentelemetry/resourcesNo proxy
These SDKs do not proxy your calls. They only send analytics data to PostHog in the background.
-
2
Set up the OpenTelemetry exporter
Required
Initialize the OpenTelemetry SDK with PostHog's
PostHogTraceExporter. This sendsgen_ai.*spans directly to PostHog's OTLP ingestion endpoint. PostHog converts these into$ai_generationevents automatically.import { NodeSDK } from '@opentelemetry/sdk-node' import { resourceFromAttributes } from '@opentelemetry/resources' import { PostHogTraceExporter } from '@posthog/ai/otel' const sdk = new NodeSDK({ resource: resourceFromAttributes({ 'service.name': 'my-ai-app', }), traceExporter: new PostHogTraceExporter({ apiKey: '<ph_project_token>', host: 'https://us.i.posthog.com', }), }) sdk.start() -
3
Call Vercel AI with telemetry enabled
Required
Pass
experimental_telemetryto your Vercel AI SDK calls. Theposthog_distinct_idmetadata field links events to a specific user in PostHog.import { generateText } from 'ai' import { openai } from '@ai-sdk/openai' const result = await generateText({ model: openai('gpt-5-mini'), prompt: 'Tell me a fun fact about hedgehogs.', experimental_telemetry: { isEnabled: true, functionId: 'my-ai-function', metadata: { posthog_distinct_id: 'user_123', // optional }, }, }) console.log(result.text) await sdk.shutdown()Note: If you want to capture LLM events anonymously, omit the
posthog_distinct_idmetadata field. See our docs on anonymous vs identified events to learn more.You can expect captured
$ai_generationevents 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 |
-
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
-
4
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