"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""

from __future__ import annotations
from .percentilelatencycutoffs import (
    PercentileLatencyCutoffs,
    PercentileLatencyCutoffsTypedDict,
)
from typing import Any, Union
from typing_extensions import TypeAliasType


PreferredMaxLatencyTypedDict = TypeAliasType(
    "PreferredMaxLatencyTypedDict", Union[PercentileLatencyCutoffsTypedDict, float, Any]
)
r"""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."""


PreferredMaxLatency = TypeAliasType(
    "PreferredMaxLatency", Union[PercentileLatencyCutoffs, float, Any]
)
r"""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."""