basic_fallback.py
Run the Example
1
Set up your virtual environment
2
Install dependencies
3
Export your API keys
4
Run the example
Save the code above as
basic_fallback.py, then run:Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
When the primary model fails (after exhausting its own retries), fallback models are tried in order until one succeeds.
"""
Fallback Models — Basic
=============================
When the primary model fails (after exhausting its own retries),
fallback models are tried in order until one succeeds.
"""
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.models.openai import OpenAIChat
# ---------------------------------------------------------------------------
# Basic: pass a list of fallback models directly
# The primary model points to an unreachable server so it will fail
# with a connection error, then the fallback (Claude) handles the request.
# ---------------------------------------------------------------------------
agent = Agent(
model=OpenAIChat(id="gpt-4o", base_url="http://localhost:1/v1", retries=0),
fallback_models=[Claude(id="claude-sonnet-4-20250514")],
)
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
agent.print_response("What is the meaning of life?", stream=True)
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
Install dependencies
uv pip install -U agno anthropic openai
Export your API keys
export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
Run the example
basic_fallback.py, then run:python basic_fallback.py
Was this page helpful?