> ## Documentation Index
> Fetch the complete documentation index at: https://docs.befailproof.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Compare model latency, tokens, context use, and traffic distribution.

Use Models to see whether reliability or cost changed with a model, agent, environment, or time range.

<Tabs>
  <Tab title="Dashboard">
    1. Go to **Observe → Models**.
    2. Set the time range, then filter by environment, model, agent, or session ID.
    3. Review latency, token consumption, context-window use, and model distribution.
    4. Select a chart point or distribution segment to open the matching events.

           <img src="https://mintcdn.com/exosphere/WgPwQzedeDNwJBTy/images/dashboard/models.png?fit=max&auto=format&n=WgPwQzedeDNwJBTy&q=85&s=db49dfc29def4a8418110c9ea4b67afc" alt="The Models page showing latency, percentile, token, cost, context-window, and model-distribution views." width="3200" height="2000" data-path="images/dashboard/models.png" />
  </Tab>

  <Tab title="CLI">
    ```bash theme={null}
    fp list models
    fp events --event-type model_request,model_response --env production --since 24h
    fp --json events --fields ts,agent_id,session_id,event_type,output_tokens,context_fill
    ```

    Use a saved query for model-level aggregates that are not exposed as a dedicated CLI command.
  </Tab>
</Tabs>