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

# Analytics quick start

> Check traffic health and estimate the savings from routing to a candidate model.

Use Analytics to confirm how a task is serving traffic and estimate the cost of sending the same usage to another model.

<Note>
  Before you begin, send representative requests through the task. Configure model prices when Studio can't identify them automatically so cost comparisons have sufficient pricing coverage.
</Note>

<Steps>
  <Step title="Select a time range">
    Open the task's **Analytics** page and choose a range from one hour through three months. Use a range that represents the traffic you expect the candidate to serve.
  </Step>

  <Step title="Check traffic health">
    Review request volume, routed model share, task versions, token volume, and provider errors. Resolve unexpected errors or routing changes before comparing costs.
  </Step>

  <Step title="Check pricing coverage">
    Confirm that the models you want to compare have similar pricing coverage, so the cost comparison in the next step reflects both models accurately. Add a manual price in provider or fine-tune settings when Studio can't find a price.
  </Step>

  <Step title="Compare model costs">
    In the cost calculator, select a comparison model. Review the estimated cost and savings if all traffic in the selected range had used that model.

    Treat the result as an estimate. Use evaluations and application metrics to confirm that a less expensive model preserves the quality your task requires.
  </Step>

  <Step title="Monitor a rollout">
    After changing routing, confirm that the candidate receives the intended share, errors remain stable, and estimated cost moves in the expected direction.
  </Step>
</Steps>

<Card title="Analytics metrics and pricing" href="/model-distillation/studio/analytics" arrow="true">
  Learn how Studio calculates traffic, token, error, and cost views.
</Card>