Claude + Groq GPT-OSS

Pair Claude Sonnet 4.5 with Groq's GPT-OSS 120B as a reasoning model to compare 9.11 and 9.9.

Use a currently available model for your Groq account. This sample uses GPT-OSS reasoning; the former Qwen3-32B and Scout examples are retired on ordinary developer tiers.

The separate Groq stage passes its answer text to Claude as reasoning context. The current Groq adapter does not map the provider’s separate native reasoning field into Agno’s reasoning content, so this example does not forward that field.

Add the following code to your Python file

groq_plus_claude.py
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.models.groq import Groq

reasoning_agent = Agent(
    model=Claude(id="claude-sonnet-4-5"),
    reasoning_model=Groq(
        id="openai/gpt-oss-120b",
        request_params={"reasoning_effort": "medium", "include_reasoning": True}
    ),
)
reasoning_agent.print_response("9.11 and 9.9 -- which is bigger?", stream=True)

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Install dependencies

uv pip install -U agno groq anthropic

Export your Groq and Anthropic API keys

  export GROQ_API_KEY="your_groq_api_key_here"
  export ANTHROPIC_API_KEY="your_anthropic_api_key_here"

Run Agent

python groq_plus_claude.py