Llama 4 Maverick

131 000 context

Model ID

meta-llama/llama-4-maverick-17b-128e-instruct-fp8

Use It in Python

from openai import OpenAI

client = OpenAI(
    base_url="https://us-south.ml.cloud.ibm.com/ml/v1/text/chat?version=2025-02-11",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Other free options: see every provider serving this model. Don't have a key yet? See how to get one — IBM watsonx.ai (Lite plan) asks for a payment card at sign-up.

Free Tier Limits (IBM watsonx.ai (Lite plan))

Rate Limit
About 2 requests/second (Lite)
Daily Limit
300,000 tokens/month + 20 CUH/month