Opsmeter.io
AI Cost & Inference Control
Integration docs
Implementation guide for AI cost control
Ship telemetry fast, keep attribution stable, and move from ingest to governance without changing your app network path.
Recommended path
Start with direct ingest, validate one stable payload shape, then harden budgets, retries, and incident workflows.
What this page answers
- How to branch n8n workflows on workspace status and budget flags.
- What a blocked ingest response means for downstream automation.
- Which templates cover status checks, ingest, and Slack-style alerts.
Implementation rhythm
5 minfirst ingest path
No proxyapp path unchanged
One schemaacross providers
Use quickstart for initial payloads, then operations docs to harden production workflows.
n8n integration
Use workspace status booleans directly in n8n If nodes. No string casting is required.
| Field | n8n use |
|---|---|
isPlanLimitReached | Pause or reroute telemetry pipelines. |
telemetryPaused | Show clear operator message in Slack/Discord/email. |
isBudgetWarning | Send early warning notification. |
isBudgetExceeded | Trigger escalation flow. |
severity | Single branch key (normal/warning/critical). |
Status check workflow (example)
- HTTP Request node calls
GET /v1/diagnostics/workspace-statuswithX-API-Key. - If node checks
$json.telemetryPausedand$json.isBudgetExceeded. - Slack/Discord/email nodes notify the correct channel.
{
"method": "GET",
"url": "https://api.opsmeter.io/v1/diagnostics/workspace-status",
"headers": {
"X-API-Key": "YOUR_WORKSPACE_API_KEY"
}
}Ingest branch for 402
Provider calls should continue. Branch only telemetry behavior when ingest returns 402.
if ($json.statusCode === 402 && $json.body.reason === "plan_limit_reached") {
// pause telemetry retries; notify owner/admin
}Ready-to-import templates: n8n workflow templates.