List Traces

Retrieve a paginated list of execution traces with optional filtering.

Traces provide observability into:

• Agent execution flows
• Model invocations and token usage
• Tool calls and their results
• Errors and performance bottlenecks

Filtering Options:

• By run, session, user, or agent ID
• By status (OK, ERROR)
• By time range

Pagination:

• Use page (1-indexed) and limit parameters
• Response includes pagination metadata (total_pages, total_count, etc.)

Response Format: Returns summary information for each trace. Use GET /traces/{trace_id} for detailed hierarchy.

GET /traces

List Traces

cURL

curl --request GET \
  --url https://api.example.com/traces \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.example.com/traces"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.example.com/traces', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/traces",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/traces"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.example.com/traces")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/traces")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

200

{
  "data": [
    {
      "trace_id": "a1b2c3d4",
      "name": "Stock_Price_Agent.run",
      "status": "OK",
      "duration": "1.2s",
      "start_time": "2025-11-19T10:30:00.000000+00:00",
      "total_spans": 4,
      "error_count": 0,
      "input": "What is the stock price of NVDA?",
      "run_id": "run123",
      "session_id": "session456",
      "user_id": "user789",
      "agent_id": "agent_stock",
      "created_at": "2025-11-19T10:30:00+00:00"
    }
  ],
  "meta": {
    "page": 1,
    "limit": 20,
    "total_pages": 5,
    "total_count": 95
  }
}

{
  "detail": "Bad request",
  "error_code": "BAD_REQUEST"
}

{
  "detail": "Unauthenticated access",
  "error_code": "UNAUTHENTICATED"
}

{
  "detail": "Not found",
  "error_code": "NOT_FOUND"
}

{
  "detail": "Validation error",
  "error_code": "VALIDATION_ERROR"
}

{
  "detail": "Internal server error",
  "error_code": "INTERNAL_SERVER_ERROR"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

run_id · string | null

Filter by run ID

session_id · string | null

Filter by session ID

user_id · string | null

Filter by user ID

agent_id · string | null

Filter by agent ID

team_id · string | null

Filter by team ID

workflow_id · string | null

Filter by workflow ID

status · string | null

Filter by status (OK, ERROR)

start_time · string | null

Filter traces starting after this time (ISO 8601 format with timezone, e.g., '2025-11-19T10:00:00Z' or '2025-11-19T15:30:00+05:30'). Times are converted to UTC for comparison.

end_time · string | null

Filter traces ending before this time (ISO 8601 format with timezone, e.g., '2025-11-19T11:00:00Z' or '2025-11-19T16:30:00+05:30'). Times are converted to UTC for comparison.

page · integer · default: 1

Page number (1-indexed)

Required range: x >= 0

limit · integer · default: 20

Number of traces per page

Required range: x >= 1

db_id · string | null

Database ID to query traces from

Response

200

application/json

List of traces retrieved successfully

data · TraceSummary · object[] · required

List of items for the current page

Show child attributes

meta · PaginationInfo · object · required

Pagination metadata

Show child attributes