---
title: "Execute Custom ML Endpoint"
url: https://docs.catalyst.zoho.com/en/sdk/python/v1/quickml/execute-custom-ml-endpoint/
description: "This page describes the method to execute QuickML endpoints in your Python application with a sample code snippet."
last_updated: 2026-09-15T05:25:35Z
service: QuickML
type: general
related_links:
  - name: "QuickML Help"
    url: /en/quickml/
  - name: "QuickML Pipeline Endpoints"
    url: /en/quickml/help/pipeline-endpoints/
  - name: "SDK Scopes"
    url: /en/sdk/python/v1/sdk-scopes
---

The code snippet given below allows you to pass input data to a published  [QuickML endpoint](https://docs.catalyst.zoho.com/en/quickml/help/pipeline-endpoints/) , and get the inferences from the ML model .  The output returns the prediction of the values of the target column that is defined while creating the ML pipeline.   

> **Note:** 

1. You will need to have the ML pipeline and the model's endpoint configured and published in your project using the Catalyst console, before you execute this code to predict the outcome with the code snippet below.

2. QuickML is currently available to Catalyst users accessing from the US, IN, EU, JP, SA, or CA data centers.

The  _quickml component instance_  is created as shown, which will not fire a server-side call. You will need to create a data dictionary through which you can pass the input data to the model’s endpoint as key-value pairs. The dictionary keys must match the features from your trained dataset that is expected by the model. The endpoint_key mentioned is the unique ID of the endpoint published for the ML model configured in your project.
The endpoint key and the input data are passed to the  `run_inference` ( endpoint_key, input_data)   method for execution.  The app reference used in the code below  is the  [ python object](https://docs.catalyst.zoho.com/en/sdk/python/v1/setup/#initializing-the-sdk) returned as a response during SDK initialization.   
**Sample Code Snippet**

```python
# Create a QuickML instance.
quickml = app.quick_ml()

    # Run Inference

    # Replace with your endpoint key copied from the Catalyst console.
    endpoint_key = "<ENDPOINT_KEY>"

    # Replace the sample feature names and values with the input expected by your model.
input_data = {
  "<FEATURE_1>": "<VALUE_1>",
  "<FEATURE_2>": "<VALUE_2>"
}

response = quickml.run_inference (endpoint_key, input_data)

print(response)

```

**The syntax of the model response received is shown below:**

```json
{
   "status": "success",
  "result": [
    {
      "prediction": "1",
      "confidence": 0.87
    }
  ]
}
```

**Parameters Used**

<table style="width:100%; border: 1px solid #ccc; border-collapse: collapse; font: 15px/24px zoho-puvi-regular;">
  <thead>
    <tr style="background-color: #f2f2f2;">
      <th style="border: 1px solid #ccc; padding: 10px; text-align: left; font: 15px/24px zoho-puvi-semibold;">Parameter Name</th>
      <th style="border: 1px solid #ccc; padding: 10px; text-align: left; font: 15px/24px zoho-puvi-semibold;">Definition</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td style="border: 1px solid #ccc; padding: 10px; text-align: left; font: 15px/24px zoho-puvi-semibold;">endpoint_key</td>
      <td style="border: 1px solid #ccc; padding: 10px;">A mandatory parameter. Will store the unique ID of the endpoint published for the ML model.</td>
    </tr>
    <tr>
      <td style="border: 1px solid #ccc; padding: 10px; text-align: left; font: 15px/24px zoho-puvi-semibold;">input_data</td>
      <td style="border: 1px solid #ccc; padding: 10px;">A mandatory parameter. Will pass the required data input to the endpoint.</td>
    </tr>
  </tbody>
</table>

> **Note:** The  predict(endpoint_key, input_data)  method continues to be supported for existing implementations and performs the same operation as  run_inference(endpoint_key, input_data_) .
We recommend using  run_inference()  in new implementations for consistency with the other QuickML SDK methods.

**Where to find the endpoint information?**   
Create an endpoint for your trained ML model and access the endpoint details page to view the  Endpoint URL, required headers and a sample request response.  
![quickml-python-sdk-1.webp](https://catalyst-docs-development.zohostratus.in/images/sdk/python/quickml/quickml-python-sdk-1.webp)

> **Info :** Refer to the [SDK Scopes table](https://docs.catalyst.zoho.com/en/sdk/python/v1/sdk-scopes) to determine the required permission level for performing the above operation.

---