---
title: Chat Groq
description: Run open models on Groq for fast, low-latency inference.
---

Give an AI node access to open models (such as Llama) running on Groq's very fast servers, using your own Groq API key.

Pick a saved connection in the **Authentication** field, or create one from there.

## What it does

Chat Groq is a model you plug into the **Model** slot of an AI node, such as the [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/) or [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/). It does not run on its own and has no output. When the AI node runs, it sends its messages to Groq with your key and gets the reply back.

* **Temperature** is 0 when you leave it empty, so answers are focused and repeatable.
* Replies are capped at **Max Tokens** (4096 by default).
* A failed request is retried up to **Max Retries** times (2 by default). A request that gets no answer within 60 seconds fails.

## When to use it

* Speed matters: a quick reply while you wait, or many items in a loop.
* You want open models such as Llama without running them yourself.
* Classifying or tagging lots of short texts cheaply.

## Inputs and settings

Type the **Model** id as Groq lists it, for example `llama-3.3-70b-versatile`. Groq adds and retires models often, so check its model list if a model stops working.

## Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

* **Model** slot of [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/), [Q\&A Agent](/nodes/builtin/ai/aiagents/qanode/), [RAG Agent](/nodes/builtin/ai/aiagents/ragnode/), [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/), [Indexer](/nodes/builtin/ai/aiagents/indexernode/), [Text Classifier](/nodes/builtin/ai/aiagents/textclassifiernode/), [Sentiment Analysis](/nodes/builtin/ai/aiagents/sentimentanalysisnode/), [Summarization](/nodes/builtin/ai/aiagents/summarizationchainnode/), [Information Extractor](/nodes/builtin/ai/aiagents/informationextractornode/), [Guardrails](/nodes/builtin/ai/aiagents/guardrails/), [Auto-fixing Output Parser](/nodes/builtin/ai/aidependencies/outputparser/autofixingoutputparser/)

The AI node you connect it to produces the output. Chat Groq only decides which model answers.

## Dependencies and credentials

* **Authentication** (connection): required. See [Connect Groq](/app/connections/groq/).

In **Authentication**, use a Bearer Token credential that holds your Groq API key. Create the key on the API Keys page of the Groq console. See [Create a credential](/app/connections/create/).

## Example workflow

1. A [Context Menu](/nodes/builtin/trigger/contextmenu/) trigger on selected text.
2. [Text Classifier](/nodes/builtin/ai/aiagents/textclassifiernode/) with **Text** `{{ $input.selectionText }}` and **Categories** `bug, feature request, question`.
3. Chat Groq in its **Model** slot, **Model** `llama-3.3-70b-versatile`.
4. [Browser Notification](/nodes/extension/browsernotification/) with **Message** `{{ $input.category }}`.

## Common issues

* **"Model parameter is required and cannot be empty".** Fill in **Model**.
* **A "model decommissioned" or "model not found" error.** Groq retired the model. Pick a current one from its model list.
* **A 429 "rate limit" error.** You sent too many requests or tokens per minute for your plan. Slow the workflow down (fewer items at once) or upgrade the plan.
* **A 401 error.** The key is wrong or revoked. Create a new key and update the credential.

## Related nodes

* [Text Classifier](/nodes/builtin/ai/aiagents/textclassifiernode/): sort text into your categories.
* [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/): send one prompt and get a reply.
* [Ollama](/nodes/builtin/ai/aidependencies/llm/ollama/): run open models on your own computer instead.