Skip to content
Telemetry
AI operations

llm_request_completed event schema

Record a completed model call with its model, token usage, latency, allocated cost, and tool outcome. Exclude prompts and generated content.

Reviewed by the Telemetry product team on . We checked what each event represents, which service sends it, field types, sensitive data, the example, and validation steps. Who reviews this page

Test this schema

Question this event answers

What does each successful AI workflow cost and how well does it perform?

Fields
10
Required
9
Send and check an event

Record and query llm_request_completed

Document what each llm_request_completed row represents and which service sends it. Send test events to check the fields, then verify that the query answers your question.

  1. 1

    Outcome becomes final

    Shared model gateway or provider adapter emits only after token usage, outcome, and provider response are final.

  2. 2

    Choose the fields

    9 required fields preserve the declared grain: One completed model-provider request.

  3. 3

    Check the test event

    Check types, UTC time, alternate outcomes, idempotency, and every pseudonymous or review-classified field.

  4. 4

    Query the result

    What does each successful AI workflow cost and how well does it perform?

Grain

One completed model-provider request.

Owner

Shared model gateway or provider adapter

Emit when

After token usage, outcome, and provider response are final.

Field contract

Field types and data to exclude

Keep field names and types stable once production queries depend on them. Document optional fields and add them only when they answer a specific question.

FieldTypeRequiredPrivacyMeaning
timestamp_utctimestampyesnon-sensitiveUTC time when the operation finishes.
event_idstringyesnon-sensitiveStable unique identifier used for deduplication.
releasestringyesnon-sensitiveApplication or service version that emitted the event.
account_idstringyespseudonymousStable internal account identifier, never an email or name.
featurestringyesnon-sensitiveStable product feature or workflow using the model.
modelstringyesnon-sensitiveProvider model identifier.
input_tokensnumberyesnon-sensitiveProvider-reported input tokens.
output_tokensnumberyesnon-sensitiveProvider-reported output tokens.
estimated_cost_usdnumbernonon-sensitiveEstimated allocation cost, reconciled separately.
statusstringyesnon-sensitiveFinal provider or workflow outcome.

Synthetic JSON event

{
  "timestamp_utc": "2026-07-28T14:18:44Z",
  "event_id": "evt_llm_01",
  "account_id": "acct_8f31",
  "release": "2026.07.2",
  "feature": "query_explanation",
  "model": "model_family_a",
  "input_tokens": 820,
  "output_tokens": 244,
  "estimated_cost_usd": 0.0124,
  "status": "success"
}

Privacy review

Review identifiers before ingestion

This example uses synthetic identifiers. Pseudonymous values can still be personal data, and review fields can expose business or provider context. Apply your own consent, retention, access, residency, and deletion requirements.

  • account_id: pseudonymous

Validation checklist

Test the schema before building a dashboard

  • Send one known llm_request_completed fixture after the documented outcome boundary.
  • Verify all 9 required fields arrive with the documented types.
  • Retry the same event identifier and confirm the chosen deduplication behavior.
  • Send a controlled failure or alternate outcome when the workflow supports one.
  • Run the related SQL over a fixed window and reconcile the result to the fixture.

Common mistakes

Record one result per row

  • Emitting llm_request_completed before shared model gateway or provider adapter knows the final outcome.
  • Mixing different kinds of results in one table, which makes counts and rates ambiguous.
  • Replacing controlled categories with raw URLs, payloads, prompts, or error text.
  • Changing a field type in place after saved queries and dashboards depend on it.
  • Adding identifiers without a documented investigation, access, and retention need.

Use the contract

Query the event and set up monitoring

LLM economics dashboardLLM cost SQLEvent schema design guide

Related contracts

agent_tool_call_completed

Which tools fail, retry, loop, or add latency before an agent reaches a useful outcome?

Review schemauser_signed_up

Which signup cohorts activate and retain?

Review schemaproduct_milestone_completed

Which accounts complete the milestones you use to define activation?

Review schema

Send a test event before production traffic

Create a free API key, send the synthetic event, and inspect the inferred table before connecting a live workflow.

Test this schema