Send and verify events with Anthropic Claude API telemetry
Use Anthropic Claude API telemetry where your app knows the final result. Collect only the fields you need, then verify a test event before building charts.
- 1
Choose the outcome
Claude API cost analytics
- 2
Define the contract
provider, model, feature, and status
- 3
Log the final result
Read the model from the API response and configuration instead of hard-coding a soon-to-age model identifier in analytics.
- 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
- The official Anthropic TypeScript SDK configured server-side
- A server-side TELEMETRY_API_KEY
- A product workflow and reviewed outcome definition
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.
npm installation
npm install telemetry-sh- 1Create one reusable server-side client. Set its timeout and retry limit.
- 2Log an event when the operation succeeds, fails, retries, or times out.
- 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.
Anthropic Claude API telemetry event
const startedAt = performance.now();
const message = await anthropic.messages.create({
model: process.env.ANTHROPIC_MODEL,
max_tokens: 1024,
messages,
});
await telemetry.log("llm_request_completed", {
provider: "anthropic",
model: message.model,
feature: "support_reply",
status: "success",
stop_reason: message.stop_reason,
input_tokens: message.usage.input_tokens,
output_tokens: message.usage.output_tokens,
latency_ms: Math.round(performance.now() - startedAt),
prompt_version: "support-v3",
release: process.env.APP_RELEASE,
});Event schema
provider, model, feature, and status
input_tokens, output_tokens, latency_ms, and stop_reason
run_id, prompt_version, reviewer_outcome, and release
Check your setup
Checkpoint 1
Read the model from the API response and configuration instead of hard-coding a soon-to-age model identifier in analytics.
Checkpoint 2
Log the request outcome after usage and stop reason are known, and log failures with a controlled error type.
Checkpoint 3
Keep raw prompts, completions, API keys, and tool payloads out of telemetry.
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.
Anthropic Claude API telemetry verification query
SELECT *
FROM llm_request_completed
ORDER BY timestamp_utc DESC
LIMIT 20;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
Event schemas for this workflow
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.
Measure AI agent task success and human handoff
Which agent workflows finish successfully and produce accepted outcomes?
Open recipeCalculate LLM cost by feature and model
Which product features and models are driving LLM spend?
Open recipeMeasure LLM cache savings and retry cost
How much model cost is associated with retries and cache misses?
Open recipeMeasure LLM time to first token
Which model and feature combinations feel slow before output begins?
Open recipeMeasure accepted AI outputs per dollar
Which model and feature combination produces the most accepted outputs per dollar?
Open recipeBrowse by implementation family
Compare related integration patterns
Templates to pair with this integration
More integrations
OpenAI agent telemetry
Log OpenAI agent runs, tool calls, model usage, latency, cost, and final outcomes with structured events.
Open guideAmazon Bedrock model telemetry
Measure Bedrock Converse requests by model or inference profile, token usage, latency, stop reason, retries, and business outcome.
Open guideOpenAI Responses API telemetry
Measure OpenAI Responses API latency, token usage, tool activity, failures, and downstream outcomes without collecting prompts or generated content.
Open guide