OpenRouter Observability & Monitoring with OpenTelemetry

SigNoz has released a guide for setting up OpenRouter observability using OpenTelemetry, enabling developers to track LLM API requests, latency, and usage across multiple models in unified dashboards. The integration allows users to configure alerts on latency and errors by broadcasting traces from OpenRouter to an OpenTelemetry Collector and exporting them to SigNoz cloud or self-hosted instances. This observability setup aims to help teams monitor every model request and gain actionable insights to improve reliability and responsiveness in AI workflows.

What is OpenRouter Observability? OpenRouter observability gives you full visibility into your LLM API routing across multiple models. This guide walks you through setting up OpenRouter monitoring using OpenTelemetry https://opentelemetry.io/ and exporting traces to SigNoz, so you can track requests, latency, and usage across your OpenRouter applications. With full OpenRouter observability in SigNoz, you can correlate traces across your AI and LLM workflows, configure alerts on latency and errors, and gain actionable insights to continuously improve reliability and responsiveness. SigNoz brings your OpenRouter telemetry into unified dashboards so you can monitor every model request in one place. Prerequisites - A SigNoz Cloud account https://signoz.io/teams/ with an active ingestion key or Self Hosted SigNoz instance https://signoz.io/docs/install/self-host/ - Internet access to access OpenRouter API and send telemetry data to SigNoz Cloud - An OpenRouter account https://openrouter.ai/ and OpenRouter API key. You can get it from the OpenRouter API Keys page https://openrouter.ai/settings/keys . Set Up OpenRouter Observability with OpenTelemetry Step 1: Configure broadcasting traces from OpenRouter to OTel Collector For more information on setting up traces from OpenRouter refer to the OpenRouter broadcast guide https://openrouter.ai/docs/guides/features/broadcast/otel-collector . Enable Broadcast in OpenRouter Go to Settings Observability https://openrouter.ai/settings/observability and toggle Enable Broadcast. Configure OpenTelemetry Collector Click 'Add Destination +' next to the OpenTelemetry Collector entry and enter: Endpoint : https://ingest.<region .signoz.cloud:443/v1/traces Headers : { "signoz-ingestion-key": "<your-ingestion-key " } <region : Your SigNoz Cloud region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint <your-ingestion-key : Your SigNoz ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ For self-hosted collector: - Deploy your OpenTelemetry Collector with an OTLP receiver - Configure the receiver to listen on a publicly accessible endpoint - Add the endpoint URL - Remove the ingestion key header as shown in Cloud → Self-Hosted https://signoz.io/docs/ingestion/cloud-vs-self-hosted cloud-to-self-hosted . Test and Save Click Test Connection to verify the setup. Once there is a success message, click the "Add" button. Once configured, your OpenRouter calls are traced and sent to SigNoz. Step 2: Use the OpenRouter API For more information on getting started with OpenRouter in your environment, refer to the OpenRouter quickstart guide https://openrouter.ai/docs/quickstart . python import requests import json response = requests.post url="https://openrouter.ai/api/v1/chat/completions", headers={ "Authorization": "Bearer <OPENROUTER API KEY ", "HTTP-Referer": "<YOUR SITE URL ", Optional. Site URL for rankings on openrouter.ai. "X-Title": "<YOUR SITE NAME ", Optional. Site title for rankings on openrouter.ai. }, data=json.dumps { "model": "openai/gpt-5.2", Optional "messages": { "role": "user", "content": "What is SigNoz?" } } fetch 'https://openrouter.ai/api/v1/chat/completions', { method: 'POST', headers: { Authorization: 'Bearer <OPENROUTER API KEY ', 'HTTP-Referer': '<YOUR SITE URL ', // Optional. Site URL for rankings on openrouter.ai. 'X-Title': '<YOUR SITE NAME ', // Optional. Site title for rankings on openrouter.ai. 'Content-Type': 'application/json', }, body: JSON.stringify { model: 'openai/gpt-5.2', messages: { role: 'user', content: 'What is SigNoz', }, , } , } ; curl https://openrouter.ai/api/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENROUTER API KEY" \ -d '{ "model": "openai/gpt-5.2", "messages": { "role": "user", "content": "What is SigNoz?" } }' View OpenRouter Traces in SigNoz Once configured, your OpenRouter application automatically emits traces. OpenRouter traces are available in SigNoz under the Traces tab: When you click on a trace in SigNoz, you'll see a detailed view of the trace, including all associated spans, along with their events and attributes. Troubleshooting OpenRouter Observability Troubleshooting OpenRouter Observability troubleshooting-openrouter-observability If you don't see your telemetry data: Verify network connectivity - Ensure your application can reach OpenRouter API and SigNoz Cloud endpoints Check ingestion key - Verify your SigNoz ingestion key is correct Wait for data - OpenTelemetry batches data before sending, so wait 10-30 seconds after making API calls OpenRouter Monitoring Dashboard The OpenRouter Dashboard Template https://signoz.io/docs/dashboards/dashboard-templates/openrouter-dashboard/ provides ready-made visualizations for monitoring OpenRouter usage. It includes pre-built charts for LLM request volume, token usage, and cost, along with import instructions to get started quickly. Setup OpenTelemetry Collector Optional Setup OpenTelemetry Collector Optional setup-opentelemetry-collector-optional What is the OpenTelemetry Collector? Think of the OTel Collector as a middleman between your app and SigNoz. Instead of your application sending data directly to SigNoz, it sends everything to the Collector first, which then forwards it along. Why use it? Cleaning up data — Filter out noisy traces you don't care about, or remove sensitive info before it leaves your servers. Keeping your app lightweight — Let the Collector handle batching, retries, and compression instead of your application code. Adding context automatically — The Collector can tag your data with useful info like which Kubernetes pod or cloud region it came from. Future flexibility — Want to send data to multiple backends later? The Collector makes that easy without changing your app. See Switch from direct export to Collector https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/switch-to-collector/ for step-by-step instructions to convert your setup. For more details, see Why use the OpenTelemetry Collector? https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/why-to-use-collector/ and the Collector configuration guide https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/configuration/ . Additional resources: - Set up alerts https://signoz.io/docs/product-features/alert-management for high latency or error rates - Learn more about querying traces https://signoz.io/docs/product-features/trace-explorer - Explore log correlation https://signoz.io/docs/product-features/logs-explorer