Export Model Usage

This endpoint exports AI model usage data including token consumption, costs per model, request counts, and response times.

Try it (cURL):

curl

curl --request POST \
  --url https://api.langdock.com/export/models \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "from": {
    "date": "2024-01-01T00:00:00.000Z",
    "timezone": "UTC"
  },
  "to": {
    "date": "2024-01-31T23:59:59.999Z",
    "timezone": "UTC"
  }
}
'

Response example (200):

response.json

{
  "success": true,
  "data": {
    "filePath": "assistants-usage/workspace-id/assistants-usage-2024-01-01-2024-01-31-abc12345.csv",
    "downloadUrl": "https://storage.example.com/signed-url",
    "dataType": "assistants",
    "recordCount": 1250,
    "dateRange": {
      "from": "2024-01-01T00:00:00.000Z",
      "to": "2024-01-31T23:59:59.999Z"
    }
  }
}

---

Data included

The model export contains:

• AI models used (GPT-4, Claude, etc.)

• Token consumption per model

• Cost per model

• Request counts

• Response times

• Error rates by model

• Usage patterns over time

---

Cost analysis

The model export is particularly valuable for cost analysis and optimization. You can use this data to:

• Identify the most expensive models in your usage

• Track cost trends over time

• Optimize model selection for different use cases

• Budget for future AI model usage

Additional details on prerequisites, rate limits, and export size limits are in the main Usage Export API documentation: https://docs.langdock.com/api-endpoints/usage-export/intro-to-usage-export-api

---

1

Request

POST /export/models

Description: Export model usage data.

Example request body (application/json):

{
  "from": {
    "date": "2024-01-01T00:00:00.000Z",
    "timezone": "UTC"
  },
  "to": {
    "date": "2024-01-31T23:59:59.999Z",
    "timezone": "UTC"
  }
}

2

Headers

• Authorization (string, required) API key as Bearer token with USAGE_EXPORT_API scope. Format: "Bearer YOUR_API_KEY"

• Content-Type: application/json

3

Response (200)

Successful response fields:

• success (boolean) — indicates if the export was successful. Example: true

• data (object)

  • data.filePath (string) — Path to the generated export file. Example: "assistants-usage/workspace-id/assistants-usage-2024-01-01-2024-01-31-abc12345.csv"

  • data.downloadUrl (string) — Signed URL to download the export file. Example: "https://storage.example.com/signed-url"

  • data.dataType (enum) — Type of data exported. Options: assistants, users, workflows, projects, models. Example: "assistants"

  • data.recordCount (integer) — Number of records in the export. Example: 1250

  • data.dateRange (object)

    • data.dateRange.from (string) — Start date of the export. Example: "2024-01-01T00:00:00.000Z"

    • data.dateRange.to (string) — End date of the export. Example: "2024-01-31T23:59:59.999Z"

---

Status codes

• 200 — Export successful

• 400 — Bad request

• 401 — Unauthorized

• 404 — Not found

---

Related: Export Project Usage — https://docs.langdock.com/api-endpoints/usage-export/export-projects

Was this page helpful? Yes / No