ScaledThought
← All models

Meta

Llama 4 Maverick

Live · US + CAtextimageLlama 4 Community License

Meta's 128-expert natively multimodal MoE, still widely deployed as a dependable workhorse.

Price per 1M tokens

Input

$0.27

Cached input

—

Output

$0.85

Priced per model · Same in US and CA · Free tier included · Pricing

Specs

Model id
llama-4-maverick
Weights released
Apr 5, 2025
Parameters
400B total · 17B active
Architecture
MoE
Context
1M tokens (1,000,000)
Input
text, image
License
Llama 4 Community License
Regions
us, ca

Benchmarks

Independent scores aren't published yet. They'll appear here as soon as they are.

Sources: ai.meta.com · huggingface.co · artificialanalysis.ai

Use it

Three lines of code, or zero.

OpenAI-compatible. Use the model id below, or auto to let the router decide when this model is worth it.

Quickstart→
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
resp = client.chat.completions.create(
    model="llama-4-maverick",
    messages=[{"role": "user", "content": "Hello"}],
)

Opens your agent with the prompt typed. You press Enter.