Keep agents running through provider failures with automatic fallback models

Agents and teams can now be configured with fallback models that activate automatically when the primary model fails, whether from rate limits, outages, context window overflows, or other retryable errors. Fallbacks are tried in order after the primary model’s retry loop is fully exhausted, and each fallback model runs its own independent retry cycle before the next one is attempted. Both simple lists and error-specific routing are supported, giving teams full control over how failures are handled.

Pass fallback_models to any Agent or Team. If the primary model fails after exhausting its retries, each fallback is tried in order until one succeeds.

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.models.openai import OpenAIChat

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    fallback_models=[Claude(id="claude-sonnet-4-20250514")],
)

‍

If gpt-4o fails after exhausting its own retries, Claude is tried automatically.

Model strings work too:

from agno.agent import Agent

agent = Agent(
    model="openai:gpt-4o",
    fallback_models=["anthropic:claude-sonnet-4-20250514"],
)

‍

See Fallback Models docs for more.