Llama 3.3 70B

llama-3.3-70b-versatile

Fast Llama inference on Groq.

Try in Playground API docs

Drop-in OpenAI compatibility

Use one model ID.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.text-generator.io/v1",
    api_key="YOUR_TEXT_GENERATOR_KEY",
)

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Hello"}],
)