View Token Factory usage statistics

Last update: October 23 2026Open in Markdown

You can view Token Factory usage statistics:

• view general statistics — total number of requests and consumed tokens for the selected period broken down by API keys and models;

• view statistics for leaders by requests — five models or API keys that processed the most requests during the selected period, with information about consumed tokens;

• view details for each request — identification data, response time, and token consumption for each request.

View general statistics

1. In the control panel, in the top menu, click Products and select Token Factory.

2. In the Token Factory section, open the Statistics tab.

3. Select the period for which statistics will be displayed. You can choose a period from predefined ranges or specify a custom one.

4. Optional: filter statistics by API keys.

5. Optional: filter statistics by models.

6. View the statistics.

   Parameter	Description
   Number of requests	Total number of completed requests
   Total tokens	Total number of consumed tokens
   Input tokens	Total number of input tokens
   Output tokens	Total number of output tokens
   Reasoning tokens	Total number of tokens generated during the reasoning phase (only for reasoning models)
   Cached tokens	Total number of tokens read from the cache

View statistics for leaders by requests

You can view the five models or API keys that processed the most requests during the selected period, with information about consumed tokens.

Models

1. In the control panel, in the top menu, click Products and select Token Factory.

2. In the Token Factory section, open the Statistics tab.

3. Select the period for which statistics will be displayed. You can choose a period from preset ranges or specify a custom one.

4. Optional: filter statistics by API keys.

5. Optional: filter statistics by models.

6. In the Leaders by requests block, open the Models tab. The five models that processed the most requests during the selected period will be displayed.

7. View statistics for each model.

   Parameter	Description
   Requests	Total number of requests processed by the model
   Input tokens	Total number of input tokens
   Output tokens	Total number of output tokens
   Cached tokens	Total number of tokens read from the cache
   Reasoning tokens	Total number of tokens generated during the reasoning phase (only for reasoning models)
   Total tokens	Total number of tokens consumed when processing requests by the model

Keys

1. In the control panel, in the top menu, click Products and select Token Factory.

2. In the Token Factory section, open the Statistics tab.

3. Select the period for which statistics will be displayed. You can choose a period from preset ranges or specify a custom one.

4. Optional: filter statistics by API keys.

5. Optional: filter statistics by models.

6. In the Leaders by requests block, open the Keys tab. The five API keys with the most requests during the selected period will be displayed.

7. View statistics for each API key.

   Parameter	Description
   Requests	Total number of requests made with the API key
   Input tokens	Total number of input tokens
   Output tokens	Total number of output tokens
   Cached tokens	Total number of tokens read from the cache
   Reasoning tokens	Total number of tokens generated during the reasoning phase (only for reasoning models)
   Total tokens	Total number of consumed tokens for the API key

View details of each request

1. In the control panel, in the top menu, click Products and select Token Factory.

2. In the Token Factory section, open the Statistics tab.

3. Select the period for which statistics will be displayed. You can choose a period from preset ranges or specify a custom one.

4. Optional: filter statistics by API keys.

5. Optional: filter statistics by models.

6. In the Activity block, view the details of each request. Requests are displayed for the selected period in descending date order.

   Parameter	Description
   Date	Date and time of request execution
   Key	API key specified in the request
   Request ID	Unique request identifier
   Model	Identifier of the model that processed the request
   Response time, ms	Time from receiving the request to full completion of the response in milliseconds
   Input tokens	Number of input tokens
   Output tokens	Number of output tokens
   Cached tokens	Number of tokens read from the cache
   Reasoning tokens	Number of tokens generated during the reasoning phase (only for reasoning models)