LangSmith

​

Step 1: Get your LangSmith API key and Project name

​

Step 2: Enable Broadcast in OpenRouter

​

Step 3: Configure LangSmith

• Api Key: Your LangSmith API key (starts with lsv2_pt_...)
• Project: Your LangSmith project name
• Endpoint (optional): Default is https://api.smith.langchain.com. Change for self-hosted instances

​

Step 4: Test and save

​

Step 5: Send a test trace

• Input and output messages
• Token usage (prompt, completion, and total tokens)
• Cost information
• Model and provider information
• Timing and latency metrics

​

What data is sent

• GenAI semantic conventions: Model name, token counts, costs, and request parameters
• LangSmith-specific attributes: Trace name, span kind, user ID, and custom metadata
• Input and output: Prompt and completion content on the run as langsmith.span.input / langsmith.span.output and gen_ai.prompt / gen_ai.completion. The root run no longer carries a duplicate copy under langsmith.trace.input / langsmith.trace.output.
• Error handling: Exception events with error types and messages when requests fail

​

Custom Metadata

​

Supported Metadata Keys

​

Tags

​

Example

{
  "model": "openai/gpt-4o",
  "messages": [{ "role": "user", "content": "Analyze this text..." }],
  "user": "user_12345",
  "session_id": "session_abc",
  "trace": {
    "trace_id": "analysis_workflow_123",
    "trace_name": "Text Analysis Pipeline",
    "span_name": "Sentiment Analysis",
    "generation_name": "Extract Sentiment",
    "environment": "production",
    "team": "nlp-team"
  }
}

​

Run Types

• GENERATION → llm run type
• SPAN → chain run type
• EVENT → tool run type

​

Additional Context

• The user field maps to LangSmith’s User ID
• The session_id field maps to LangSmith’s Session ID for conversation tracking
• Custom metadata keys are passed as span attributes and viewable in the run details

​

Privacy Mode