n8n Groq Chat Model nodeConfigure Groq Chat Model in n8n.
The n8n Groq Chat Model node supplies the language model an AI node runs on. It exposes 2 parameters, a Model picker loaded live from the Groq API and an Options collection, and it attaches to the Model port of an agent or a chain. Built for anyone wiring a first agent.
Verified Trustpilot reviews · AI, automation & growth agency
What does the n8n Groq Chat Model node actually do?
The Groq Chat Model node hands a language model to another node. It has no main input of its own and never runs on its own: you drop it on the canvas, drag its connector to the Model port of a root node, and that root node calls Groq every time it needs text. A sub-node is exactly that, a node that only exists to serve the one above it. Pick the model, and the work happens upstairs.
Take a lead qualification flow. Rows land from Google Sheets, an agent reads each company description and returns a score, and the outreach goes out through Gmail. The agent is the node that thinks; Groq Chat Model is what it thinks with. Set Model once and every item in the run goes through the same model.
Second case, a support triage. A message arrives, a classifier sorts it into a handful of buckets, and the result is posted to Slack. Classification wants stable output, so the Sampling Temperature option goes low and stays there. Third case, a retrieval chat: a question and answer chain pulls passages from a vector store and asks the model to answer from them, with Maximum Number of Tokens capping how long that answer can run.
When would you skip this node? When the model you want lives somewhere else. The Model port accepts one sub-node at a time, so OpenAI, Anthropic and Google Gemini each have their own chat model sub-node and you swap one for another by moving the connector. Nothing else in the workflow has to change, which makes the swap a fair way to compare behavior on your own data.
The limits are worth knowing before you build. This node carries no main input, so it cannot sit in the middle of a chain of regular nodes and it produces no items you can inspect between steps. Its parameter surface is deliberately thin: a model and two options, nothing about retries, system prompts or tools. Those belong to the root node, the AI Agent or the chain you attached it to. And the model list is loaded from the Groq API at the moment you open the dropdown, so it reflects what your credential can reach, not a list frozen in the node.
Cost sits on the provider side: Groq bills its own API calls under its own terms, and n8n adds nothing on top whether you run n8n Cloud or your own Docker instance.
What do you need to connect before the node runs?
- 01
Create the Groq credential
Open the Credentials menu in n8n and create a credential for Groq. A credential in n8n is a saved set of authentication details, stored apart from the workflow so the key never sits in a node you might export or share. You create it once and reuse it in every workflow that calls Groq, on n8n Cloud and on a self-hosted instance alike.
- 02
Select it on the node
Open the Groq Chat Model node and pick that credential in the credential selector at the top of the panel. The node has no Authentication dropdown to choose between methods, so this one selection is the whole authentication step. Until a working credential is attached, the Model dropdown has nothing to show: it asks the Groq API for the list and needs the key to do it.
- 03
Wire it to a root node
Drag the connector at the bottom of the node onto the Model port of the root node that will use it. A port is the small labelled anchor under a root node where sub-nodes attach. Groq Chat Model has no main input, so there is nothing to connect on its left side and no way to trigger it directly. Run the root node to test, not this one.
Where does the Groq Chat Model node plug in?
n8n splits AI work between a root node that receives the workflow items and sub-nodes that attach to its ports, one type of sub-node per port.
Output (what it plugs into)
- Model
ai_languageModel
01Model
This is the only connection the node has, and it goes upward: the node offers itself on the ai_languageModel port of a root node, which then calls Groq whenever it needs to generate text.
Key parameters
- Required: a root node cannot run without a chat model on this port, so the connection is not optional.
- AI Agent and Basic LLM Chain: the two usual starting points, an agent that can call tools and a chain that just prompts the model.
- Question and Answer Chain and Summarization Chain: retrieval answers and long-document summaries.
- Text Classifier and Information Extractor: sorting items, and pulling structured fields out of free text.
How do you set the 2 parameters?
The Groq Chat Model node has 2 parameters. For each one: the node as you configure it in n8n, what the parameter changes, and our field notes.
Model
modelWhat you see in n8n
Notes & use cases
Picks which Groq model generates the completion. n8n loads the available models from the Groq API when you open the dropdown, so the list reflects your account rather than a hardcoded set baked into the node.
Key parameters
- Model: a dropdown of the models the Groq API returns for your credential; you can also set it from an expression such as
{{ $json.model }}when the choice travels with the item.
Options
optionsWhat you see in n8n
Notes & use cases
A collection that stays empty until you add something to it. Leave it alone and Groq applies its own defaults; open Add Option and you control how long the answer runs and how predictable it is.
Key parameters
- Maximum Number of Tokens: the ceiling on the tokens generated in the completion, a token being the chunk of text a model reads and writes. It caps answer length, which matters when the output lands in a field with a size limit.
- Sampling Temperature: controls randomness. Lower it and completions get less random; near zero the model turns deterministic and repetitive.
Need help automating Groq Chat Model with n8n?
A person reads every message.
Groq Chat Model in n8n, the questions that come next
01Is the Groq Chat Model node included in n8n?
02What do you need to make the n8n Groq Chat Model node work?
03What are the limits of this node?
04What do you attach at minimum, and which sub-node should a beginner start with?
05n8n or Make for running a Groq model?
Get our weekly integration tips.
No spam. Unsubscribe anytime.
