# Call a Prompt

> Learn how to call your Prompts that are managed on Humanloop.

This guide will show you how to call your Prompts through the API, enabling you to generate responses from the large language model while versioning your Prompts.

You can call an existing Prompt on Humanloop, or you can call a Prompt you're managing in code. These two use-cases are demonstrated below.

### Prerequisites

<Accordion title="Install and initialize the SDK">
  First you need to install and initialize the SDK. If you have already done this, skip to the next section.

  Open up your terminal and follow these steps:

  1. Install the Humanloop SDK:

  <CodeBlock>
    ```python
    pip install humanloop
    ```

    ```typescript
    npm install humanloop
    ```
  </CodeBlock>

  2. Initialize the SDK with your Humanloop API key (you can get it from the [Organization Settings page](https://app.humanloop.com/account/api-keys)).

  <CodeBlock>
    ```python
    from humanloop import Humanloop
    humanloop = Humanloop(api_key="<YOUR HUMANLOOP KEY>")

    # Check that the authentication was successful
    print(humanloop.prompts.list())
    ```

    ```typescript
    import { HumanloopClient, Humanloop } from "humanloop";

    const humanloop = new HumanloopClient({ apiKey: "YOUR_API_KEY" });

    // Check that the authentication was successful
    console.log(await humanloop.prompts.list());
    ```
  </CodeBlock>
</Accordion>

## Call an existing Prompt

If you don't have Prompt already on Humanloop, please follow our [Prompt creation](/docs/development/guides/create-prompt) guide first.

<Steps>
  ### Get the Prompt ID

  In Humanloop, navigate to the Prompt and copy the Prompt ID by clicking Prompt name in the top bar, and copying from the popover.

  <img src="https://files.buildwithfern.com/https://humanloop.docs.buildwithfern.com/docs/2025-08-13T04:13:40.157Z/assets/images/prompts/prompt-call-1-copy-id.png" />

  ### Call the Prompt by ID

  Now you can use the SDK to generate completions and log the results to your Prompt:

  This can be done by using the [Prompt Call](/docs/api/prompts/call) method in the SDK.

  <EndpointRequestSnippet endpoint="POST /prompts/call" example="By ID" />

  <EndpointResponseSnippet endpoint="POST /prompts/call" example="By ID" />
</Steps>

## Call a Prompt defined in code

You can also manage your Prompts in code. Pass the `prompt` details within your API call to generate responses with
the specified parameters.

<EndpointRequestSnippet endpoint="POST /prompts/call" example="Supplying Prompt" />

<EndpointResponseSnippet endpoint="POST /prompts/call" example="Supplying Prompt" />

## View your Prompt Logs

Navigate to the **Logs** tab of your Prompt.
You will be able to see the recorded inputs, messages and model generations.

## Next steps

* [Iterate and improve on your Prompts](../evals/comparing-prompts) in the Editor
* [Capture end-user feedback](../observability/capture-user-feedback) to monitor your model performance.