Resources · Make integration

DeepSeek AI Make integrationAutomate DeepSeek AI with Make.

Want DeepSeek to write replies, summaries or code inside the tools your team already uses? The DeepSeek AI Make integration gives you 4 modules, no trigger, and an API key is all it takes. This guide connects your account and walks you through a first working scenario.

Try the DeepSeek AI integration on MakeSee the 4 modules

Verified Trustpilot reviews · AI, automation & growth agency

What you can automate

What can the DeepSeek AI Make integration do?

The DeepSeek AI Make integration lets a Make scenario (the automation you build, a chain of steps) send text to a DeepSeek model and pass the answer to your other apps. Each step is a module, and DeepSeek brings four of them: one to get a response, one to list models, one to read your balance and one for any other API call.

Replies drafted before anyone opens the ticket. A support team routes each new message into Create a Chat Completion and gets a draft answer back, ready to review in the helpdesk or a shared inbox. The model writes, a person decides.

A model catalog that stays accurate. List Models returns the models your account can call, one bundle (one item passed to the next module) per model. Store them in a table, for example through the Airtable Make integration, so whoever builds prompts picks from the real list.

A credit check before a big batch. Put Get Balance at the start of a scenario that will generate many completions, and look at what it returns before the heavy work starts.

What the app does not do: it has no trigger, so DeepSeek never starts a scenario by itself. Another app or Make’s own schedule starts it. The doc lists no numeric limit for these modules either. Anything outside the four modules goes through Make an API Call. If you are still choosing a tool, read our n8n vs Make comparison, and the Make pricing page explains how operations are counted.

Connect

How do you connect DeepSeek AI to Make?

  1. 01

    Create an API key in DeepSeek

    Log in to your DeepSeek AI Platform account and open API keys in the left sidebar. Click Create new API key, give it a name you will recognize, confirm with Create API key, then copy the value.

  2. 02

    Add a DeepSeek AI module in Make

    In your scenario, add any DeepSeek AI module and click Create a connection. A connection is your DeepSeek account linked to Make once, then reused by every DeepSeek module. The Connection name field is optional.

  3. 03

    Paste the key and save

    Paste the key into the API Key field and click Save. If Make asks you to authenticate or confirm access, accept it. The connection now appears in the module, and the other DeepSeek modules can pick it from the list.

First scenario

Your first scenario with DeepSeek AI and Make

GoalWhen a new message lands in the app your team already uses, Make asks DeepSeek AI for a draft reply.

  1. 01

    Create the scenario

    Open the Scenarios page, create a new scenario and click the +. DeepSeek has no trigger, so the first module comes from the app where your messages arrive: a form, an inbox or a helpdesk.

  2. 02

    Add Create a Chat Completion

    Click the + on the right of that first module, search for DeepSeek AI and pick Create a Chat Completion. Select the connection you created, or click Create a connection if you skipped that part.

  3. 03

    Map the incoming text

    Fill the module fields and map the text of the incoming message from the first module into them. Mapping means Make drops the value of the previous step into this field on every run, instead of a fixed text.

  4. 04

    Test with Run once

    Click Run once and send yourself a test message. Make runs the scenario one time and shows the bundles each module received, so you can read the draft DeepSeek wrote before anything goes further.

  5. 05

    Schedule and switch it on

    Open the clock on the first module to set the schedule, every 15 minutes by default, then switch the scenario on. From then on, each new message gets its draft without anyone copying and pasting prompts.

Modules

What the DeepSeek AI modules do in Make

DeepSeek AI gives you 4 modules in 2 groups. For each one: what it does for you, when to reach for it, and what to watch out for.

DeepSeek AI

3 modules
DeepSeek AI1

Create a Chat Completion

Action

In Make“Creates a model response for the given chat completion.”

You send a conversation to a DeepSeek model and get its written answer back as a bundle the next module can use. This is the module that actually produces text or code.

When to use it
whenever an event in another app should end with generated text, like a ticket needing a first reply or a product brief needing a description.
Watch out
each bundle that reaches it runs it once and counts as one operation on your Make plan.
DeepSeek AI2

List Models

Search

In Make“Returns a list of models.”

This search returns the models your DeepSeek account can reach, one bundle per model, so you see exactly what is available instead of guessing a name.

When to use it
before you set up Create a Chat Completion, or when you keep a reference table of models for the people who write prompts.
Watch out
a search can return zero, one or several bundles, and every module placed after it runs once per bundle.
DeepSeek AI3

Get Balance

Action

In Make“Returns the user's balance information.”

Get Balance reads the balance information of your DeepSeek account and hands it to the next module, so a scenario can know where your credit stands.

When to use it
at the start of a scenario that sends many texts to DeepSeek, or in a small scenario that posts the balance to the channel your team reads.
Watch out
it returns information and nothing more, so add a module from another app after it if someone needs an alert.

Other

1 module
DeepSeek AI4

Make an API Call

Action

In Make“Performs an arbitrary authorized API Call.”

With this module you call any endpoint of the DeepSeek API yourself, using the same connection as the other three modules, without setting up a key again.

When to use it
when the task you need is not covered by Create a Chat Completion, List Models or Get Balance.
Watch out
you write the request by hand, so keep the DeepSeek API documentation open next to the module while you fill it.
Need help

Need help automating DeepSeek AI with Make?

A person reads every message.

FAQ

DeepSeek AI and Make: common questions

01Is the DeepSeek AI Make integration free?
Yes, on the Make side. DeepSeek AI is a standard app, available from the Free plan like the other 3,000+ standard apps. The Free plan allows 2 active scenarios, runs them at most every 15 minutes, stops a run after 5 minutes, handles files up to 5 MB and 512 MB of data transfer. Paid plans (Core, Pro, Teams, Enterprise) go down to a 1 minute interval and allow 40 minutes per run. Make counts usage in operations, one per module run on one bundle. What DeepSeek itself charges on your account is outside this page; Get Balance shows where your balance stands.
02What do you need to connect DeepSeek AI to Make?
A DeepSeek AI Platform account and an API key. In DeepSeek, open API keys in the left sidebar, click Create new API key, name it, confirm and copy the value. In Make, add a DeepSeek AI module, click Create a connection, paste the key in the API Key field and click Save; the connection name is optional. If Make asks you to authenticate or confirm access, accept it. That single connection then works for all 4 modules, including Make an API Call, so you only go through these steps once.
03Does DeepSeek AI trigger a Make scenario in real time?
No, because the app has no trigger module. DeepSeek never starts a scenario on its own. You start it in one of two ways. Put the trigger of another app first, for example a form or a helpdesk, and DeepSeek works on what that app sends. If that trigger is instant, the other app calls Make by webhook as soon as something happens. Or rely on Make’s own schedule: a new scenario runs every 15 minutes by default, and the Free plan cannot go below that interval, while paid plans go down to 1 minute.
04What if a DeepSeek AI module is missing in Make?
Use Make an API Call. It is one of the 4 modules of the app and lets you call any endpoint of the DeepSeek API with the same connection, so you do not need a second key. The listed modules cover chat completions, the model list and your balance; anything else goes through that module, with the DeepSeek API documentation open to build the request. The Make doc lists no numeric limit for these modules, so there is no quota to plan around on the Make side beyond your plan and its operations.
05Should you use Make or n8n for DeepSeek AI?
It depends on the tool your team already works in, not on DeepSeek. In Make you get 4 ready modules: Create a Chat Completion, List Models, Get Balance and Make an API Call, a Free plan to start, and a visual editor where you test with Run once. Many apps also have an n8n node, so check that side before you decide if n8n is already in place. We do not rank the two for this app. Compare how each one counts runs and how your team likes to build, then pick the one you will maintain.
Same platform

Other docs you might need on this stack.

Browse all integrations