library · inferred from evidence
ModelFallbackMiddleware
Middleware for falling back to alternative models when the primary model fails.
- ModelRateLimitError: handling provider rate limits without hammering the API
Rate limit errors are retryable, and LangChain retries 429s automatically up to 6 times by default. If you still get ModelRateLimitError, you need to slow down at the source with a rate limiter, reduce concurrency, or spread load across pro