dynamic_model_router.py
"""
This example demonstrates how to use dynamic model router with OpenRouter.
Dynamic models provide automatic failover when the primary model encounters:
- Rate limits
- Timeouts
- Unavailability
- Model overload
OpenRouter will automatically try the models defined in order until one succeeds.
"""
from agno.agent import Agent
from agno.models.openrouter import OpenRouter
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
# Create an agent with dynamic models
# If the primary model fails, OpenRouter will automatically try the models defined in order
agent = Agent(
model=OpenRouter(
id="anthropic/claude-sonnet-4", # Primary model
models=[
"deepseek/deepseek-r1", # First fallback model
"openai/gpt-4o", # Second fallback model
],
),
markdown=True,
)
# Run the agent - it will use the primary model if available,
# or automatically fall back to alternative models if needed
agent.print_response("Write a short poem about resilience and backup plans")
# You can also check which model was actually used in the response
# by examining the response metadata (if available from OpenRouter)
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
pass
Run the Example
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Install dependencies
uv pip install -U agno openai
3
Export your OpenRouter API key
export OPENROUTER_API_KEY="your_openrouter_api_key_here"
$Env:OPENROUTER_API_KEY="your_openrouter_api_key_here"
4
Run the example
Save the code above as
dynamic_model_router.py, then run:python dynamic_model_router.py