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

# Test a model

> Send prompts directly to models in Model Chat.

Model Chat lets you send prompts directly to models and compare responses side by side.

## Start a conversation

<Steps>
  <Step>
    Navigate to **Playground > Model Chat** in the sidebar.
  </Step>

  <Step>
    Select **Deployments** or **Base Models** to choose the type of model to test.
  </Step>

  <Step>
    Select up to two models using the checkboxes.
  </Step>

  <Step>
    Type a message and press **Send**.
  </Step>
</Steps>

## View influential training data

For a deployed fine-tuned model, you can see which training examples shaped a response. See [Training data attribution](/flow/components/explainability/training-data-attribution).

<Steps>
  <Step>
    Select a deployed fine-tuned model under **Deployments** and send a prompt.
  </Step>

  <Step>
    Click **Influential Data** above the response.
  </Step>

  <Step>
    Review the training examples. Each one shows an influence level and the question-answer pair it came from.
  </Step>

  <Step>
    Click **Done** to close.
  </Step>
</Steps>

Each model in a side-by-side comparison has its own **Influential Data** link, so you can compare what shaped each response.

<Note>
  The link appears for any deployed fine-tuned model, including when the model has no relevant training data for the prompt. In that case the list is empty.
</Note>

## Next steps

* [Chat with an agent](/flow/app/chat-with-an-agent) – Test agents in Agent Chat


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.