ActionGroqUpdated May 2026

How do I call Groq for LLM inference?

Short answer: Drop the "Groq → Groq Chat Completion" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 4 Groq actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model model	options	Required	Model. Options: Llama 3.3 70B, Llama 3.1 8B (fastest), Llama 3 70B, Mixtral 8x7B, Gemma 2 9B
Message message	string	Required	Message. Example: Explain quantum computing in simple terms
System Prompt system_prompt	string	Optional	System Prompt. Example: You are a helpful assistant.
Temperature temperature	string	Optional	0 = deterministic, 2 = very creative
Max Tokens max_tokens	string	Optional	Max Tokens. Example: 1024

Sample request

{
  "model": "{{trigger.model}}",
  "message": "e.g. Explain quantum computing in simple terms",
  "system_prompt": "e.g. You are a helpful assistant.",
  "temperature": "e.g. 0.7",
  "max_tokens": "e.g. 1024"
}

Returns

{
  "id": "chatcmpl-abc",
  "model": "llama-3.3-70b-versatile",
  "usage": {
    "total_tokens": 170,
    "prompt_tokens": 20,
    "completion_tokens": 150
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses..."
      },
      "finish_reason": "stop"
    }
  ]
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Groq Chat Completion.

Any of these apps can fire this action as part of a workflow.

2 Google Sheets triggers

HubSpot → Groq

18 HubSpot triggers

FAQ

Questions about Groq Chat Completion.

What does the Groq Chat Completion action do in Groq?

Runs chat completion at Groq's custom-LPU-hardware speed (1000+ tokens/sec on Llama 3.3 70B). For latency-sensitive workflows where the speed advantage stacks across multi-step agent chains.

What inputs does Groq Chat Completion require?

Required: Model, Message. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Groq returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Groq Chat Completion support batch operations?

Yes. Run Groq Chat Completion inside a Loop node to process arrays. Tiny Command handles Groq's rate limits automatically so you don't have to throttle manually.

More actions