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);

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
}

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}")

// 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" } },
    ],
  }],
});

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
  };
}