Skip to content
Telemetry
Integration guide

Vercel AI SDK telemetry

Track streaming completions, token usage, retries, latency, and accepted results from AI SDK workflows.

Reviewed by the Telemetry product team on . We checked which events to send, which data to exclude, and how to add the code. Who reviews this page

Ready to connect model usage to accepted product outcomes? Review the OpenAI cost tracking guide.

Useful for
  • Streaming LLM analytics
  • Feature cost reporting
  • Reliability dashboards
Test the integration

Send and verify events with Vercel AI SDK telemetry

Use Vercel AI SDK telemetry where your app knows the final result. Collect only the fields you need, then verify a test event before building charts.

  1. 1

    Choose the outcome

    Streaming LLM analytics

  2. 2

    Define the contract

    feature, provider, model, prompt_version, and finish_reason

  3. 3

    Log the final result

    Record the final generation result after the stream finishes so token usage and finish reason are complete.

  4. 4

    Check the stored event

    Exercise a known fixture, then inspect llm_request_completed for one correctly typed terminal row.

Before you start

Before you start

  • AI SDK generation or streaming calls running on your server
  • A stable feature and prompt-version taxonomy for comparing generations
  • An allowlist for telemetry metadata that excludes prompts, responses, headers, and tool payloads

Delivery setup

Install and initialize server-side

Import telemetry-sh in server-only code and initialize it once with process.env.TELEMETRY_API_KEY. Keep ingestion credentials out of browser bundles, client-visible environment variables, source control, logs, and exception messages.

vercel-ai-sdk-install

npm installation

bash
npm install telemetry-sh
  1. 1Create one reusable server-side client. Set its timeout and retry limit.
  2. 2Log an event when the operation succeeds, fails, retries, or times out.
  3. 3Send test events with known results and inspect the stored rows before enabling an alert.

Snippet

Start with one structured event

Add this shape where the workflow completes, fails, or retries. Then build the dashboard from real fields.

vercel-ai-sdk

Vercel AI SDK telemetry event

javascript
await telemetry.log("llm_request_completed", {
  provider: "openai",
  model: "gpt-4.1-mini",
  feature: "draft_reply",
  prompt_version: "draft-reply-v4",
  input_tokens: 924,
  output_tokens: 218,
  latency_ms: 1380,
  finish_reason: "stop",
  status: "success",
  accepted: true,
});

Event schema

feature, provider, model, prompt_version, and finish_reason

input_tokens, output_tokens, total_tokens, estimated_cost_usd, and latency_ms

status, retry_count, time_to_first_token_ms, accepted, and release

Check your setup

Checkpoint 1

Record the final generation result after the stream finishes so token usage and finish reason are complete.

Checkpoint 2

Use AI SDK lifecycle callbacks or a telemetry integration for consistent coverage instead of duplicating ad hoc logging around every call.

Checkpoint 3

Review the SDK's experimental telemetry behavior during upgrades and explicitly exclude prompt, response, request-header, and tool-argument attributes.

Verification

Prove the event arrived

Run this after exercising known success and failure cases. Replace the fallback table name if your final event contract differs from the snippet.

vercel-ai-sdk-verification

Vercel AI SDK telemetry verification query

sql
SELECT *
FROM llm_request_completed
ORDER BY timestamp_utc DESC
LIMIT 20;
Confirm one terminal row per logical outcome, with the expected status, identifiers, units, and UTC time.
Inspect the inferred schema and verify that retries do not change field types or generate a new logical event ID.
Search the stored fields for credentials, raw payloads, prompts, private content, and unbounded error messages.
Exercise a provider timeout, ingestion rejection, and process shutdown before treating the dashboard as complete.

Implementation references

Review the event contract, data-safety guidance, and upstream primary documentation before enabling a new production path.

Where to log

Keep the outcome event small and recoverable

This pattern provides

  • Record the outcome as an event you can query with SQL.
  • Stable fields for dashboards, alerts, and cross-event correlation.
  • Test events for checking success, failure, retries, and timeouts.

This pattern does not provide

  • An OTLP exporter, automatic collection pipeline, or replacement for detailed traces and diagnostic logs.
  • Exactly-once delivery merely because the payload contains an event ID.
  • Permission to collect raw provider payloads, user content, credentials, or regulated data.

Example event schemas

Check what each event records, when to send it, and which field types it needs. Review the example payload and privacy checklist before using it in production.

Use these queries in Telemetry

Learn about AI agent monitoring

Query agent events to compare tool use, model costs, and outcomes for each run.

Related SQL recipes

More SQL recipes

Run the query using this workflow's event fields and check the example result. Save the result to a dashboard or set up an alert.

Browse all recipes
Recipe collectionsAI and LLM SQL

Browse by implementation family

Compare related integration patterns

Templates to pair with this integration

More integrations