create_log_export
Set up a log export definition specifying filters like time range, cost, and model, and choose fields to include. Use start_log_export to begin processing.
Instructions
Create a log export definition with filters and requested fields. This only sets up the export and does not start processing; call start_log_export next, then use get_log_export or download_log_export to inspect or retrieve the finished result.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| workspace_id | No | Workspace ID for the export | |
| description | No | Human-readable description for the export job | |
| time_min | Yes | Minimum time filter in date format (e.g., '2024-01-01' or ISO 8601) | |
| time_max | Yes | Maximum time filter in date format (e.g., '2024-01-31' or ISO 8601) | |
| cost_min | No | Minimum cost filter | |
| cost_max | No | Maximum cost filter | |
| total_units_min | No | Minimum total units (tokens) filter | |
| total_units_max | No | Maximum total units (tokens) filter | |
| ai_model | No | Filter by specific AI model names | |
| requested_fields | Yes | Fields to include in export: id, trace_id, created_at, request, response, is_success, ai_org, ai_model, req_units, res_units, total_units, request_url, cost, cost_currency, response_time, response_status_code, mode, config, prompt_slug, metadata |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | Whether the tool call succeeded and returned structured data | |
| data | No | Structured success payload when ok is true | |
| error | No | Structured error payload when ok is false |