Logo
Using
UsingDebugging API Requests

Debugging API Requests

To debug the requests sent to translation providers (like ChatGPT, Claude or Google Translate) and their responses, you can enable the 🔵 Info severity level in the settings for Logs & Notifications.

Enable Info severity in Logs & Notifications settings
Enable Info severity in Logs & Notifications settings

Accessing the API Requests Logs

The logs will be stored under the api-requests entries.

AI requests in the Logs
AI requests in the Logs

What's Logged

For AI providers, the api-requests entry contains detailed information about:

  • The prompt sent to the AI provider
  • The complete response received
  • Any errors or issues during the communication
  • The model used
  • The number of tokens used
Detail of an AI request in the Logs
Detail of an AI request in the Logs

For instance, the following "Additional context" JSON shows the details of a request sent to Claude, and its response:

{
  "request": {
    "model": "claude-3-7-sonnet-latest",
    "max_tokens": 128000,
    "messages": [
      {
        "role": "user",
        "content": "You are a language translator.\r\n\r\nI'm working on internationalizing my application.\r\n\r\nI've created a JSON with sentences in English. Please translate the sentences to Spanish from Argentina.\r\n\r\nIf a sentence contains HTML, do not translate inside the HTML tags.\n\nReturn ONLY a JSON object with a single key \"translations\" containing an array of translated strings.\nDo not include any explanations, markdown formatting, or code blocks.\nThe response must be a valid JSON object starting with { and ending with }.\n\nThis is the JSON:\n\n[\"HTTP caching improves performance\",\"Categories Block\",\"Latest Posts Block\",\"Democratizing publishing\"]"
      }
    ]
  },
  "response": {
    "id": "msg_01EC2Qp2fMw6VQY8tGESFrh2",
    "type": "message",
    "role": "assistant",
    "model": "claude-3-7-sonnet-20250219",
    "content": [
      {
        "type": "text",
        "text": "{\n  \"translations\": [\n  \"El caché HTTP mejora el rendimiento\",\n  \"Bloque de categorías\",\n  \"Bloque de entradas recientes\",\n  \"Democratizando la publicación\"\n  ]\n}"
      }
    ],
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "usage": {
      "input_tokens": 138,
      "cache_creation_input_tokens": 0,
      "cache_read_input_tokens": 0,
      "output_tokens": 61,
      "service_tier": "standard"
    }
  }
}