Rate limits
What 429 and 503 mean, and how to avoid them.
429 Too Many Requests: your traffic is above your rate limit. Limits adapt to your usage, so increase your traffic gradually.503 Service Overloaded: the model has no free capacity at that moment. The priority tier (munito-service-tier: priority) makes a 503 less likely, and overflow can answer the request in another way.
Both answers carry a Retry-After header. Wait that long before you retry. The OpenAI and Anthropic clients do this for you.
Each response carries your current limits in the x-ratelimit-* headers. For higher limits, contact us through Support in the console.