Logs export feature is only available for Production and Enterprise users.
Portkey offers an in-app logs export feature that is not generally available yet. If you’re interested in early access, contact us at support@portkey.ai.
Requesting Logs Export
To submit a data export request, simply follow these steps:- Ensure you are an admin of your organization on Portkey.
- Send an email to support@portkey.ai with the subject line
Logs Export - [Your_Organization_Name]
. - In the email body,
- Specify the time frame for which you require the logs data. Pro plan supports logs export of last 30 days.
- Share names of the specific columns you require (see the “Exported Data” section below for a complete list of available columns).
- Our team will process your request and provide you with the exported logs data in JSON format.
Note: Portkey only supports data exports in the
JSONL
format, and can not process exports in any other formats at the moment.Exported Data
The exported logs data will include the following columns:Column Name | Column Description / Property |
---|---|
created_at | Timestamp of the request |
request.body | Request JSON payload (as seen in the Portkey logs) |
response.body | Response JSON payload (as seen in the Portkey logs) |
is_success | Request success status (1 = success, 0 = failure) |
ai_org | AI provider name |
ai_model | AI model name |
req_units | Number of tokens in the request |
res_units | Number of tokens in the response |
total_units | Total number of tokens (request + response) |
cost | Cost of the request in cents (USD) |
cost_currency | Currency of the cost (USD) |
request_url | Final provider API URL |
request_method | HTTP request method |
response_status_code | HTTP response status code |
response_time | Response time in milliseconds |
cache_status | Cache status (SEMANTIC HIT, HIT, MISS, DISABLED) |
cache_type | Cache type (SIMPLE, SEMANTIC) |
stream_mode | Stream mode status (TRUE, FALSE) |
retry_success_count | Number of retries after which request was successful |
trace_id | Trace ID for the request |
mode | Config top level strategy (SINGLE, FALLBACK, LOADBALANCE) |
provider | Provider used for the request |
runtime | Runtime environment |
runtime_version | Runtime environment version |
sdk_version | Portkey SDK version |
config | Config ID used for the request |
prompt_slug | Prompt ID used for the request |
prompt_version_id | Version number of the prompt template slug |
metadata.key | Custom metadata key |
metadata.value | Custom metadata value |