Make Integration

Make is a visual automation platform for connecting apps and transforming data in workflows called scenarios. You can call any LLM API model from a scenario with Make's built-in HTTP app.

This guide sends a POST request to LLM API's OpenAI-compatible Chat Completions endpoint, tests the response, and makes the generated text available to later modules.

Prerequisites

An LLM API account with an API key
A Make account with permission to create or edit scenarios
A scenario with a trigger or other source data if you want to build a dynamic prompt

Call LLM API from a Scenario

Get Your LLM API Key

Open the LLM API dashboard.
Click Create Key to Start.
Copy the new API key. It is shown only once.
Store the key securely, such as in a password manager.

WARNING

Treat your API key like a password. Do not include it in screenshots, scenario names, or fields sent to later modules.

Add the HTTP Module

Open an existing Make scenario or create a new one.
Add and test the trigger if the prompt will use data from an earlier module.
Click + where you want to add the AI request.
Search for and select HTTP.
Select Make a request.

Use the current HTTP module rather than an OpenAI module so you can set the LLM API endpoint and request body directly.

Configure the Endpoint

Enter these values in the HTTP module:

Field	Value
Authentication type	`No authentication`
URL	`https://api.llmapi.ai/v1/chat/completions`
Method	`POST`

Configure the LLM API URL and POST method in Make

The authentication type is set to No authentication because the next step adds the required Bearer token as a request header.

Add the Authorization Header

Under Headers, add one header:

Name	Value
`Authorization`	`Bearer YOUR_LLM_API_KEY`

Replace YOUR_LLM_API_KEY with the key copied from the LLM API dashboard. Keep Bearer followed by one space before the key.

Add the LLM API Bearer token to the Authorization header

WARNING

Anyone who can edit this module may be able to view its header value. Restrict access to the scenario and replace the key immediately if it is exposed.

Add the JSON Request Body

Configure the body fields:

Body content type: application/json
Body input method: JSON string

Paste this into Body content:

{
  "model": "claude-opus-4-8",
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ],
  "max_tokens": 1024
}

Configure the JSON chat completion request body in Make

You can use any model available to your API key. Copy its exact ID from the models page and replace claude-opus-4-8 if needed.

To create a dynamic prompt, click inside the content string and map data from the trigger or another earlier module. Keep the mapped value inside the JSON string's quotation marks and make sure the completed body remains valid JSON.

INFO

Run the earlier module once if its fields do not appear in Make's mapping panel. Make needs sample output before it can offer those values to later modules.

Test the Request

Save the HTTP module.
Click Run once in the scenario editor.
Trigger the scenario or run the HTTP module with sample data.
Open the HTTP module's output bubble.
Confirm that Status Code is 200.
Expand Data, choices, the first item, and message.
Confirm that role is assistant and content contains the generated text.

A successful LLM API response in Make's HTTP module

The generated text is returned at choices[0].message.content. The request also appears in your LLM API usage analytics.

Use the Response in Another Module

Add the next module, such as Gmail, Slack, Google Sheets, or a database app.
Click the destination field that should receive the generated text.
Expand the HTTP module's output in the mapping panel.
Select content from message in the first item under choices.
Run the scenario again, then activate scheduling when the output is correct.

Each scenario run now sends its mapped input to LLM API and passes the assistant response to the remaining modules.

Troubleshooting

401 Unauthorized

Confirm that the header name is exactly Authorization.
Confirm that the value starts with Bearer , including the space.
Paste the API key again without quotation marks or leading or trailing spaces.
Verify that the key is active in the LLM API dashboard.

400 Bad Request or Invalid JSON

Set Body content type to application/json.
Set Body input method to JSON string.
Check that every JSON key and string uses double quotes.
Remove trailing commas after the final object or array item.
Make sure mapped values remain inside the content string and do not introduce unescaped quotation marks.

404 or Endpoint Error

Confirm that the URL is exactly https://api.llmapi.ai/v1/chat/completions.
Make sure the URL includes the full /v1/chat/completions path.
Confirm that Make can make outbound HTTPS requests to api.llmapi.ai.

Model Not Found or Access Denied

Copy the exact model ID from the models page.
Confirm that the API key's IAM rules allow the selected model and provider.
Make sure your LLM API account has sufficient credits.

Response Fields Are Missing from the Mapping Panel

Run the HTTP module successfully at least once so Make learns the response structure.
Confirm that the output contains parsed Data, not only an unparsed response string.
Reopen the later module after the successful test so its mapping panel refreshes.

The Request Times Out

Test with a faster model or a smaller prompt.
Reduce max_tokens if the workflow does not need a long response.
Check the LLM API dashboard to determine whether the request reached the service.

Next Steps

Map fields from earlier modules into the prompt.
Add a system message to the messages array to control the model's behavior.
Route the generated text through filters, routers, or error handlers.
Review request cost, latency, and provider routing in the LLM API dashboard.