LLM Cost Event Schema Template

Template evidence path

LLM Cost Tracker: implementation to decision

Treat the prompt as an implementation brief. The useful artifact is not copied code alone, but a reviewed event contract that produces a trustworthy answer.

1
Select the boundary
Instrument the point where llm_request_completed becomes final.
2
Create the contract
Start with llm_request_completed, llm_request_failed, llm_stream_completed and keep every field typed, bounded, and privacy-reviewed.
3
Run a fixture
Exercise known success, failure, retry, and empty-result cases before relying on aggregate results.
4
Answer the question
Which features cost the most per retained account?

Template versus use case

This page is the implementation brief

Copy this template when the measurement goal is already clear. Use the matching use-case guide to review event boundaries, success definitions, and the decisions the resulting SQL should support.

Read OpenAI Cost Monitoring

Template

Paste this into your coding agent

Replace YOUR_API_KEY, run the flow locally, then verify the generated events and dashboards.

llm-cost-tracker

LLM Cost Tracker

text

Instrument LLM usage and cost with Telemetry.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Log each model request with:
provider, model, route, feature, user_id, team_id, input_tokens, output_tokens, total_tokens, estimated_cost_usd, latency_ms, status, retry_count, and error_type.

Connect outcome events such as copied, saved, accepted, retried, regenerated, or discarded.

Create dashboards for daily spend, cost by feature, cost by account, failures by model, p95 latency, and accepted-output rate.

Do not store raw prompts or completions by default.

Events to capture

llm_request_completedllm_request_failedllm_stream_completedllm_output_savedllm_output_discarded

Verification checklist

What a complete instrumentation pass leaves behind

Events

Synthetic events reach the intended table with stable names and field types.

Queries

The first SQL queries return plausible rows with an explicit time window.

Views

A dashboard uses the real fields and includes enough context to explain a change.

Safety

Prompts, bodies, credentials, signatures, and private content were checked for redaction.

Event schema starting points

Review the row grain, emit boundary, required types, privacy classes, example payload, and validation checklist before adapting a query or snippet to production.

AI operations10 fields