About

Send a request to one gateway. If your first model reaches its quota or is temporarily unavailable, LLM API tries the next approved provider.

How it works

Pick a preferred model and fallback

Set the provider order for your workload.

Send a request

A configured fallback can take over after a quota error.

Check the result

Review the response before the workflow acts.

Use cases

Writing assistance

Draft and review text in your team’s workflow.

Document intake

Extract a draft summary and route it for review.

Developer tools

Put several authorized API accounts behind one connection.