groq-hello-world

Create a minimal working Groq chat completion example. Use when starting a new Groq integration, testing your setup, or learning basic Groq API patterns. Trigger with phrases like "groq hello world", "groq example", "groq quick start", "simple groq code".

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/groq-pack/skills/groq-hello-world/SKILL.md

Groq Hello World

Overview

Build a minimal chat completion with Groq's LPU inference API. Groq uses an OpenAI-compatible endpoint, so the API shape is familiar -- but responses arrive 10-50x faster than GPU-based providers.

Prerequisites

groq-sdk installed (npm install groq-sdk)
GROQ_API_KEY environment variable set
Completed groq-install-auth setup

Instructions

Step 1: Basic Chat Completion (TypeScript)

import Groq from "groq-sdk";

const groq = new Groq();

async function main() {
  const completion = await groq.chat.completions.create({
    model: "llama-3.3-70b-versatile",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "What is Groq's LPU and why is it fast?" },
    ],
  });

  console.log(completion.choices[0].message.content);
  console.log(`Tokens: ${completion.usage?.total_tokens}`);
}

main().catch(console.error);

Step 2: Streaming Response

async function streamExample() {
  const stream = await groq.chat.completions.create({
    model: "llama-3.3-70b-versatile",
    messages: [
      { role: "user", content: "Explain quantum computing in 3 sentences." },
    ],
    stream: true,
  });

  for await (const chunk of stream) {
    const content = chunk.choices[0]?.delta?.content || "";
    process.stdout.write(content);
  }
  console.log(); // newline
}

Step 3: Python Equivalent

from groq import Groq

client = Groq()

completion = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Groq's LPU and why is it fast?"},
    ],
)

print(completion.choices[0].message.content)
print(f"Tokens: {completion.usage.total_tokens}")

Step 4: Try Different Models

// Speed tier -- fastest responses (~560 tok/s)
const fast = await groq.chat.completions.create({
  model: "llama-3.1-8b-instant",
  messages: [{ role: "user", content: "Hello!" }],
});

// Quality tier -- best reasoning (~280 tok/s)
const quality = await groq.chat.completions.create({
  model: "llama-3.3-70b-versatile",
  messages: [{ role: "user", content: "Explain monads in Haskell." }],
});

// Vision tier -- multimodal understanding
const vision = await groq.chat.completions.create({
  model: "meta-llama/llama-4-scout-17b-16e-instruct",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "Describe this image." },
      { type: "image_url", image_url: { url: "https://example.com/photo.jpg" } },
    ],
  }],
});

Available Models (Current)

Model ID	Params	Context	Speed	Best For
`llama-3.1-8b-instant`	8B	128K	~560 tok/s	Classification, extraction, fast tasks
`llama-3.3-70b-versatile`	70B	128K	~280 tok/s	General purpose, reasoning, code
`llama-3.3-70b-specdec`	70B	128K	Faster	Same quality, speculative decoding
`meta-llama/llama-4-scout-17b-16e-instruct`	17Bx16E	128K	~460 tok/s	Vision, multimodal
`meta-llama/llama-4-maverick-17b-128e-instruct`	17Bx128E	128K	—	Best multimodal quality

Response Structure

interface ChatCompletion {
  id: string;                    // "chatcmpl-xxx"
  object: "chat.completion";
  created: number;               // Unix timestamp
  model: string;                 // Actual model used
  choices: [{
    index: number;
    message: { role: "assistant"; content: string };
    finish_reason: "stop" | "length" | "tool_calls";
  }];
  usage: {
    prompt_tokens: number;
    completion_tokens: number;
    total_tokens: number;
    queue_time: number;          // Groq-specific: seconds in queue
    prompt_time: number;         // Groq-specific: seconds for prompt
    completion_time: number;     // Groq-specific: seconds for completion
    total_time: number;          // Groq-specific: total processing seconds
  };
}

Error Handling

Error	Cause	Solution
`401 Invalid API Key`	Key not set or invalid	Check `GROQ_API_KEY` env var
`model_not_found`	Typo in model ID or deprecated model	Check model list at console.groq.com/docs/models
`429 Rate limit`	Free tier: 30 RPM on large models	Wait for `retry-after` header value
`context_length_exceeded`	Prompt + max_tokens > model context	Reduce prompt size or set lower `max_tokens`

Resources

Next Steps

Proceed to groq-local-dev-loop for development workflow setup.

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3e83543

Last updated: 2 days ago
Created: 2 days ago

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.