Short answer: Drop the "Groq → Groq Chat Completion" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
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 |
{"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"}
{"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.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.