PreferredMaxLatency - OpenRouter

Preferred maximum latency (in seconds). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints above the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold.

Supported Types

preferredMaxLatency := components.CreatePreferredMaxLatencyNumber(float64{/* values here */})

PercentileLatencyCutoffs

preferredMaxLatency := components.CreatePreferredMaxLatencyPercentileLatencyCutoffs(components.PercentileLatencyCutoffs{/* values here */})

Union Discrimination

Use the Type field to determine which variant is active, then access the corresponding field:

switch preferredMaxLatency.Type {
	case components.PreferredMaxLatencyTypeNumber:
		// preferredMaxLatency.Number is populated
	case components.PreferredMaxLatencyTypePercentileLatencyCutoffs:
		// preferredMaxLatency.PercentileLatencyCutoffs is populated
}

​Supported Types

​

​PercentileLatencyCutoffs

​Union Discrimination

Supported Types

PercentileLatencyCutoffs

Union Discrimination