Broadcast

Broadcast allows you to automatically send traces from your OpenRouter requests to external observability and analytics platforms. This feature enables you to monitor, debug, and analyze your LLM usage across your preferred tools without any additional instrumentation in your application code.

Enabling Broadcast

To enable broadcast for your account or organization:

1. Navigate to Settings > Broadcast in your OpenRouter dashboard
2. Toggle the “Enable Broadcast” switch to turn on the feature
3. Add one or more destinations where you want to send your traces

Once enabled, OpenRouter will automatically send trace data for all your API requests to your configured destinations.

Supported Destinations

The following destinations are currently available:

• Braintrust
• Datadog
• Langfuse
• S3
• Weave
• OTel Collector

Each destination has its own configuration requirements, such as API keys, endpoints, or project identifiers. When adding a destination, you’ll be prompted to provide the necessary credentials which are encrypted and stored securely.

For the most up-to-date list of available destinations, visit the Broadcast settings page in your dashboard.

Coming Soon

The following destinations are in development and will be available soon:

• Arize
• AWS Firehose
• Clickhouse
• Dynatrace
• Evidently
• Fiddler
• Galileo
• Grafana
• Helicone
• HoneyHive
• Keywords AI
• Langsmith
• Middleware
• Mona
• New Relic
• OpenInference
• Opik
• Phoenix
• Portkey
• PostHog
• Snowflake
• Supabase
• Webhook
• WhyLabs

Trace Data

Each broadcast trace includes comprehensive information about your API request:

Request & Response Data: The input messages and model output (with multimodal content stripped for efficiency)

Token Usage: Prompt tokens, completion tokens, and total tokens consumed

Cost Information: The total cost of the request

Timing: Request start time, end time, and latency metrics

Model Information: The model permaslug and provider name used for the request

Tool Usage: Whether tools were included in the request and if tool calls were made

User Tracking with Broadcast

To associate traces with specific end-users in your application, include the user field in your API requests. This identifier will be included in the broadcast trace data, allowing you to track usage patterns and debug issues for individual users.

1
{
2
  "model": "openai/gpt-4o",
3
  "messages": [
4
    {
5
      "role": "user",
6
      "content": "Hello, world!"
7
    }
8
  ],
9
  "user": "user_12345"
10
}

The user field accepts a string up to 128 characters. This identifier helps you distinguish between different users of your application in your observability platform, making it easier to investigate issues or analyze usage patterns per user.

Sampling Rate

Each destination can be configured with a sampling rate to control what percentage of traces are sent. This is useful for high-volume applications where you want to reduce costs or data volume while still maintaining visibility into your LLM usage. A sampling rate of 1.0 sends all traces, while 0.5 would send approximately 50% of traces.

Security

Your destination credentials are encrypted before being stored and are only decrypted when sending traces. Traces are sent asynchronously after requests complete, so enabling broadcast does not add latency to your API responses.

Organization Support

Broadcast can be configured at both the individual user level and the organization level. Organization admins can set up shared destinations that apply to all API keys within the organization, ensuring consistent observability across your team.