Skip to main content
The Python SDK and docs are currently in beta. Report issues on GitHub.
Percentile-based throughput cutoffs. All specified cutoffs must be met for an endpoint to be preferred.

Fields

FieldTypeRequiredDescription
p50OptionalNullable[float]:heavy_minus_sign:Minimum p50 throughput (tokens/sec)
p75OptionalNullable[float]:heavy_minus_sign:Minimum p75 throughput (tokens/sec)
p90OptionalNullable[float]:heavy_minus_sign:Minimum p90 throughput (tokens/sec)
p99OptionalNullable[float]:heavy_minus_sign:Minimum p99 throughput (tokens/sec)