# Configure model routing in LLM Proxy

Send model calls through a controlled path with provider, fallback, and policy context.

- Category: LLM Proxy
- Last updated: 2026-06-19
- URL: https://help.irongorilla.ai/articles/configure-model-routing-in-llm-proxy

## Route model calls through one governed path

LLM Proxy gives model traffic a consistent route. That route can record provider, latency, token usage, cost, [policy decisions](/articles/create-a-policy-from-plain-language), and refusal context before a response becomes part of an agent run.

## Routing setup

Use LLM Proxy to review enabled providers and model routes, then decide which teams, agents, or environments can use each route. Fallback behavior should be explicit so provider failures do not create surprise paths.

Apply [policies](/articles/create-a-policy-from-plain-language) before requests leave the boundary. Sensitive data, disallowed destinations, and high-risk model use should be handled in the route instead of left to each agent. Use an [LLM trace](/articles/read-an-llm-trace) when you need to explain one call.

## Related articles

- [Read an LLM trace](https://help.irongorilla.ai/articles/read-an-llm-trace)
- [Create a policy from plain language](https://help.irongorilla.ai/articles/create-a-policy-from-plain-language)
- [Investigate blocked actions](https://help.irongorilla.ai/articles/investigate-blocked-actions)

## Support

Need help? Tell us where you got stuck: https://help.irongorilla.ai/contact