Model fallbacks now available in Vercel AI Gateway
Vercel AI Gateway adds model fallback support, automatically trying alternative models in order when a primary model fails due to errors, capacity issues, or capability mismatches.
Vercel's now supports for when models fail or are unavailable. In addition to safeguarding against provider-level failures, model fallbacks can help with errors and capability mismatches between models (e.g., multimodal, tool-calling, etc.).AI Gatewayfallback models Fallback models will be tried in the specified order until a request succeeds or no options remain. Any error, such as context limits, unsupported inputs, or provider outages, can trigger a fallback. Requests are billed based on the model that completes successfully.
This example shows an instance where the primary model does not support multimodal capabilities, falling back to models that do. To use, specify the model fallbacks in within :modelsproviderOptions To have pre-defined provider routing in addition to model routing, specify both and providers ( or ) in :modelsorderonlyproviderOptions AI Gateway also includes built-in , , and supports .observabilityBring Your Own Key supportOpenAI-compatible API Read more