Resources · Make integration

NVIDIA Make integrationAutomate NVIDIA with Make.

Need an NVIDIA model to answer text that lands in your other tools? The NVIDIA Make integration gives you 3 modules: 2 actions and 1 search. This guide connects your account, builds a first scenario and explains each module in plain words.

Try the NVIDIA integration on MakeSee the 3 modules

Verified Trustpilot reviews · AI, automation & growth agency

What you can automate

What can the NVIDIA Make integration do for you?

The NVIDIA Make integration lets a Make scenario (the automation you build, a chain of modules) send text to an NVIDIA model and use the answer in the next step. Each module is one brick of that chain. NVIDIA brings 3 of them, and none is a trigger, so something else starts the flow.

Draft replies to incoming messages. A support form or an inbox app starts the scenario, Create a Chat Completion writes a draft, and a later module files it where your team reviews it. The model does the writing; your people keep the final word.

Check which models your account can reach. List Models returns the models available to your connection, one bundle (one item passed to the next module) per model. Handy before you pick one, and useful to log in a sheet when you audit a setup.

Reach what the menu does not show. Make an API Call calls any endpoint of the NVIDIA API with the same connection. It is the way out when the two other modules stop short.

What Make does not give you here: no trigger, so NVIDIA cannot start a scenario on its own, and the directory publishes no limits for this app. The same app has an NVIDIA n8n integration, and the n8n vs Make comparison helps you choose. If you want a guided path through the editor, the Make training starts from zero.

Connect

How do you connect NVIDIA to Make?

  1. 01

    Add an NVIDIA module

    In your scenario, click the +, search for NVIDIA and pick any of its 3 modules. Then click Create a connection. A connection is your NVIDIA account linked to Make once, and every NVIDIA module reuses it afterwards.

  2. 02

    Name the connection

    This step is optional, but a clear name pays off later. If you ever run a test account and a production account side by side, a label like the team or project name tells you which one a module is using at a glance.

  3. 03

    Authorize and save

    Make either opens the NVIDIA page to authorize access or asks you to paste the key NVIDIA gives you. Follow whichever screen appears, then click Save. The module now shows your connection and you can fill its fields.

First scenario

Build your first scenario with NVIDIA

GoalWhen a new message reaches another app, Make asks an NVIDIA model for a reply and passes it along.

  1. 01

    Create the scenario

    Open the Scenarios page, create a new scenario and click the +. Since NVIDIA has no trigger, pick the app where your messages arrive first, for example a form tool or a mailbox.

  2. 02

    Set up the starting module

    Connect that app and fill its fields. Once the connection exists, Make lists the forms, folders or sheets it can read, so you pick from a menu instead of typing a path by memory.

  3. 03

    Add Create a Chat Completion

    Click the + on the right of the first module, search NVIDIA and choose Create a Chat Completion. Create the connection, then map the message text from the previous module into its fields.

  4. 04

    Test with Run once

    Click Run once to execute the scenario a single time. Open the bubble above each module to read the bundles it received and check the NVIDIA reply before anything else depends on it.

  5. 05

    Schedule and switch on

    Set the schedule on the first module (every 15 minutes by default) and switch the scenario on. On the Free plan, 15 minutes is also the shortest interval; paid plans go down to 1 minute.

Modules

What each NVIDIA module does

NVIDIA gives you 3 modules. For each one: what it does for you, when to reach for it, and what to watch out for.

NVIDIA1

Create a Chat Completion

Action

In Make“Creates a chat completion.”

Sends your text to an NVIDIA model and gets back its written answer, ready to map into the next module. This is the module most scenarios with NVIDIA are built around.

When to use it
a customer question arrives in another app and you want a first draft of the reply waiting for your team.
Watch out
each run is one operation on your Make plan, so let only the messages that truly need an answer reach it.
NVIDIA2

Make an API Call

Action

In Make“Performs an arbitrary authorized API call.”

Opens the whole NVIDIA API from inside your scenario, reusing the connection you already created. You pick the endpoint yourself, which covers any request the two other modules do not offer.

When to use it
you found an endpoint in the NVIDIA API reference and no listed module matches it.
Watch out
keep the NVIDIA API reference open to know which endpoint to call.
NVIDIA3

List Models

Search

In Make“Returns a list of models.”

Tells you which NVIDIA models your connection can call, returning each one as a separate bundle. You get a clear inventory before you pick a model somewhere else.

When to use it
you set up a new account and want to record the available models in a sheet or a table.
Watch out
as a search, it can return zero, one or many bundles, and every following module then runs once per model.
Need help

Need help automating NVIDIA with Make?

A person reads every message.

FAQ

Questions about the NVIDIA Make integration

01Is the NVIDIA Make integration free?
Yes, on the Make side. NVIDIA is a standard app, so it is available from the Free plan, which includes 3,000+ standard apps. The Free plan caps you at 2 active scenarios, a 15 minute minimum between scheduled runs, 5 minutes of execution per run, files up to 5 MB and 512 MB of data transfer. Paid plans (Core, Pro, Teams, Enterprise) remove the scenario cap and allow 1 minute intervals. Make counts usage in operations, one per module run on one bundle. Anything NVIDIA itself charges for your account is outside the scope of this page.
02What do you need to connect NVIDIA to Make?
An NVIDIA account and a Make account. The official doc lists no prerequisite and was unavailable when this guide was written, so the steps follow Make's generic flow. Add an NVIDIA module, click Create a connection, optionally name it, then either authorize Make on the NVIDIA page or paste the key NVIDIA gives you, and click Save. That single connection then serves all 3 NVIDIA modules, so you only do this once per account.
03Does the NVIDIA Make integration react in real time?
Not by itself, because NVIDIA has no trigger in Make. The scenario has to start from something else. The first option is a trigger from another app: an instant trigger is called by that app through a webhook as soon as something happens, while a scheduled one is checked on the scenario's schedule. The second option is Make's own scheduling on the first module, every 15 minutes by default, 15 minutes minimum on the Free plan and 1 minute on paid plans. NVIDIA then acts as a step in the middle of the flow.
04What if an NVIDIA module is missing in Make?
Use Make an API Call. It reaches any endpoint of the NVIDIA API from your scenario and reuses the connection you already set up, so there is nothing new to authorize. The trade off is that you build the request yourself, following the NVIDIA API reference, instead of filling guided fields. The directory publishes no specific limit for this app, so if a call fails, read the bundle returned by Run once before changing anything. That is usually where the explanation sits.
05Should you use Make or n8n for NVIDIA?
It depends on where the rest of your automations already live. NVIDIA exists as an app in Make and as a node in n8n, so both tools can send text to an NVIDIA model. In Make you get the 3 modules described on this page, including Make an API Call for anything they miss. If your team already runs its scenarios in Make, staying there keeps every connection in one place. If your workflows already sit in n8n, the n8n node is the natural choice. The comparison page linked above lays out the differences between the two tools.
Same platform

Other docs you might need on this stack.

Browse all integrations