> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-update-deprecated-models.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Metrics

## Attributes

| Field                  | Description                                                               |
| ---------------------- | ------------------------------------------------------------------------- |
| input\_tokens          | Number of tokens in the prompt/input to the model.                        |
| output\_tokens         | Number of tokens generated by the model as output.                        |
| total\_tokens          | Total tokens used (input + output).                                       |
| audio\_input\_tokens   | Audio tokens in the input.                                                |
| audio\_output\_tokens  | Audio tokens in the output.                                               |
| audio\_total\_tokens   | Total audio tokens (if using audio input/output).                         |
| cache\_read\_tokens    | Tokens served from cache (if caching is used).                            |
| cache\_write\_tokens   | Tokens written to cache.                                                  |
| reasoning\_tokens      | Tokens used for reasoning steps (if enabled).                             |
| time\_to\_first\_token | Time until the first token is generated (in seconds).                     |
| duration               | Total run time (in seconds).                                              |
| provider\_metrics      | Provider-specific metrics (dict).                                         |
| additional\_metrics    | Any extra metrics provided by the model/tool (e.g., latency, cost, etc.). |

> Note: Not all fields are always present; it depends on the model/tool and the run.