AI & MLReal-timeUpdated May 2026

Groq

Groq fast LLM inference (Llama, Mixtral, Whisper)

Groq is the inference platform built around custom LPU (Language Processing Unit) hardware — the headline feature is dramatically faster token generation than GPU-based providers, often 5-10× the throughput of OpenAI for equivalent open-weight models. Tiny Command exposes four actions, no triggers: Chat Completion (against Llama 3.1/3.3, Mixtral 8x7B, Gemma 2, Qwen — all open-weight models served at very low latency), Analyze Image (vision-capable models like Llama 3.2 Vision serving multimodal prompts), Transcribe Audio (Whisper Large v3 at much faster than realtime), List Models. The connection uses a Groq API key from console.groq.com. The API follows the OpenAI message-array shape so workflows that have a Chat Completion structure swap models with minimal rewrite — point base URL at api.groq.com/openai/v1 instead of OpenAI's. Groq's pricing is per-token competitive with OpenAI's open-weight tier, but the latency win is the main reason to switch — workflows that chain 5-10 LLM calls finish noticeably faster.

Connect Groq

0triggers

4actions

≈ 2 minto set up

Freetier · no card

Actions

Do anything Groq can do, from a workflow.

Every action accepts dynamic inputs from upstream nodes, whether that's an AI output, a form field, or a search result.

Action	What it does	Inputs
Groq Analyze Image	Runs vision-capable LLM inference (Llama 3.2 Vision) on an image plus text prompt. Groq's LPU speed makes this fast — useful for in-flow image-classification or visual-question-answering workflows.	4 fields	View →
Groq Chat Completion	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.	5 fields	View →
List Groq Models	Returns the Groq model catalog — Llama variants, Mixtral, Gemma, plus Whisper for transcription. For model-selection workflows.	0 fields	View →
Groq Transcribe Audio (Whisper)	Whisper Large v3 hosted on Groq's LPU hardware — much faster than real-time, very cheap per minute. For high-throughput transcription workflows where speed and cost matter.	4 fields	View →

Recipes

Pre-built Groq workflows.

Clone any recipe and customize it in one click. Every recipe is fully editable.

Groq → Slack alerts

AI-triage every Groq event, ping the right channel only when it matters.

Groq → Google Sheets log

Every event matching a filter, appended to a running spreadsheet.

Groq → Notion database

Turn Groq into a Notion-backed source of truth, auto-tagged.

Before you build

Three things worth knowing.

Filter at the trigger

Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.

Authorize once, reuse anywhere

Connect Groq once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.

No JSON to read

Every Groq field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.

FAQ

Questions about the Groq integration.

If we missed yours, ping support. We usually reply within an hour.

How do I connect Groq to Tiny Command?

Open the Tiny Command workflow builder, drop in a Groq node, and click Connect. Authorize Groq once and any workflow on your account can use its triggers and actions. Most teams finish the connection in under two minutes.

What Groq triggers does Tiny Command support?

Tiny Command focuses on outbound actions for Groq today. Use Tiny Command's universal Webhook or Schedule trigger to start Groq workflows, then run any Groq action you need.

What Groq actions can I run from a workflow?

4 Groq actions are available out of the box, covering ai & ml operations like "Groq Analyze Image". Every action accepts dynamic inputs from upstream nodes, whether that's a search result, an AI output, or a form field.

Is the Groq integration real-time?

Groq actions execute synchronously inside your workflow. Tiny Command waits for Groq's API to confirm before continuing to the next step, so downstream nodes can rely on the result.

Do I need to write code to use Groq with Tiny Command?

No. Every Groq trigger and action is fully configurable from the visual workflow builder. For edge cases that aren't covered, drop in a custom HTTP node and call any Groq API endpoint directly.

How much does the Groq integration cost?

There's a free tier you can start on without a credit card. Higher run volumes and team features come with paid plans. The Groq integration itself has no per-app surcharge.