> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langtrace.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Send Trace

> Send OpenTelemetry-compatible traces to Langtrace

Send traces to Langtrace using the OpenTelemetry trace format. This endpoint accepts traces for various operations including OpenAI chat completions, function calls, and other LLM interactions.

### Headers

<ParamField header="x-api-key" type="string" required>
  Your Langtrace API key
</ParamField>

<ParamField header="Content-Type" type="string" required>
  Must be `application/json`
</ParamField>

<ParamField header="User-Agent" type="string" required>
  Must be `opentelemetry-python`
</ParamField>

### Body

<ParamField body="resourceSpans" type="array" required>
  Array of resource spans containing trace data
</ParamField>

<ParamField body="resourceSpans[].resource.attributes" type="object" required>
  Resource attributes identifying the service and environment
</ParamField>

<ParamField body="resourceSpans[].scopeSpans" type="array" required>
  Array of scope spans containing individual operation traces
</ParamField>

<ParamField body="resourceSpans[].scopeSpans[].spans" type="array" required>
  Array of spans representing individual operations
</ParamField>

### Request Example for OpenAI Chat Completion

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST 'https://app.langtrace.ai/api/trace' \
    -H 'Content-Type: application/json' \
    -H 'User-Agent: opentelemetry-python' \
    -H 'x-api-key: <LANGTRACE_API_KEY>' \
    --data-raw '{
      "resourceSpans": [{
        "resource": {
          "attributes": {
            "service.name": {
              "stringValue": "my-ai-service"
            },
            "service.version": {
              "stringValue": "1.0.0"
            }
          }
        },
        "scopeSpans": [{
          "spans": [{
            "traceId": "a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6",
            "spanId": "1234567890abcdef",
            "name": "OpenAI ChatCompletion",
            "kind": 1,
            "startTimeUnixNano": "1701555555000000000",
            "endTimeUnixNano": "1701555557000000000",
            "attributes": {
              "llm.vendor": {
                "stringValue": "openai"
              },
              "llm.request.model": {
                "stringValue": "gpt-3.5-turbo"
              },
              "llm.request.type": {
                "stringValue": "chat_completion"
              },
              "llm.request.messages": {
                "stringValue": "[{\"role\":\"user\",\"content\":\"Hello, how are you?\"}]"
              },
              "llm.response.choices": {
                "stringValue": "[{\"role\":\"assistant\",\"content\":\"I'm doing well, thank you for asking!\"}]"
              }
            }
          }]
        }]
      }]
    }'
  ```

  ```python Python theme={null}
  import json
  import requests

  url = 'https://app.langtrace.ai/api/trace'
  headers = {
      'Content-Type': 'application/json',
      'User-Agent': 'opentelemetry-python',
      'x-api-key': '<LANGTRACE_API_KEY>'
  }

  payload = {
      "resourceSpans": [{
          "resource": {
              "attributes": {
                  "service.name": {"stringValue": "my-ai-service"},
                  "service.version": {"stringValue": "1.0.0"}
              }
          },
          "scopeSpans": [{
              "spans": [{
                  "traceId": "a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6",
                  "spanId": "1234567890abcdef",
                  "name": "OpenAI ChatCompletion",
                  "kind": 1,
                  "startTimeUnixNano": "1701555555000000000",
                  "endTimeUnixNano": "1701555557000000000",
                  "attributes": {
                      "llm.vendor": {"stringValue": "openai"},
                      "llm.request.model": {"stringValue": "gpt-3.5-turbo"},
                      "llm.request.type": {"stringValue": "chat_completion"},
                      "llm.request.messages": {"stringValue": json.dumps([{"role": "user", "content": "Hello, how are you?"}])},
                      "llm.response.choices": {"stringValue": json.dumps([{"role": "assistant", "content": "I'm doing well, thank you for asking!"}])}
                  }
              }]
          }]
      }]
  }

  response = requests.post(url, headers=headers, json=payload)
  print(response.json())
  ```
</RequestExample>

### Response

<ResponseField name="status" type="number">
  HTTP status code (200 for success)
</ResponseField>

<ResponseField name="message" type="string">
  Success or error message
</ResponseField>

<ResponseExample>
  ```json Success Response theme={null}
  {
    "status": 200,
    "message": "Traces received successfully"
  }
  ```

  ```json Error Response (Invalid API Key) theme={null}
  {
    "status": 401,
    "message": "Invalid API key"
  }
  ```
</ResponseExample>

### Error Codes

<ResponseField name="401" type="string">
  Invalid or missing API key
</ResponseField>

<ResponseField name="400" type="string">
  Invalid request format or missing required fields
</ResponseField>

<ResponseField name="500" type="string">
  Internal server error
</ResponseField>