groq/compound
Groq's Compound system integrates OpenAI's GPT-OSS 120B and Llama 4 models with external tools like web search and code execution. This allows applications to access real-time data and interact with external environments, providing more accurate and current responses than standalone LLMs. Instead of managing separate tools and APIs, Compound systems offer a unified interface that handles tool integration and orchestration, letting you focus on application logic rather than infrastructure complexity.
Rate limits for groq/compound
are determined by
the rate limits of the individual models that comprise them.
Compound is powered by Llama 4 Scout and GPT-OSS 120B for intelligent reasoning and tool use.
Automatically access up-to-date information from the web using the built-in web search tool.
Execute Python code automatically using the code execution tool powered by E2B.
Experience the capabilities of groq/compound
on Groq:
pip install groq
from groq import Groq
client = Groq()
completion = client.chat.completions.create(
model="groq/compound",
messages=[
{
"role": "user",
"content": "Explain why fast inference is critical for reasoning models"
}
]
)
print(completion.choices[0].message.content)