openrouter-python-sdk-retry-errors/src/openrouter/components/generationresponse.py

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

from __future__ import annotations
from .providerresponse import ProviderResponse, ProviderResponseTypedDict
from openrouter.types import (
    BaseModel,
    Nullable,
    OptionalNullable,
    UNSET,
    UNSET_SENTINEL,
    UnrecognizedStr,
)
from pydantic import model_serializer
from typing import List, Literal, Union
from typing_extensions import NotRequired, TypedDict


APIType = Union[
    Literal[
        "completions",
        "embeddings",
        "rerank",
        "tts",
        "stt",
        "video",
        "image",
    ],
    UnrecognizedStr,
]
r"""Type of API used for the generation"""


DataRegion = Union[
    Literal[
        "global",
        "europe",
    ],
    UnrecognizedStr,
]
r"""The data region this generation was routed through. 'europe' for EU-routed requests, 'global' otherwise."""


class GenerationResponseDataTypedDict(TypedDict):
    r"""Generation data"""

    api_type: Nullable[APIType]
    r"""Type of API used for the generation"""
    app_id: Nullable[int]
    r"""ID of the app that made the request"""
    cache_discount: Nullable[float]
    r"""Discount applied due to caching"""
    cancelled: Nullable[bool]
    r"""Whether the generation was cancelled"""
    created_at: str
    r"""ISO 8601 timestamp of when the generation was created"""
    data_region: DataRegion
    r"""The data region this generation was routed through. 'europe' for EU-routed requests, 'global' otherwise."""
    external_user: Nullable[str]
    r"""External user identifier"""
    finish_reason: Nullable[str]
    r"""Reason the generation finished"""
    generation_time: Nullable[float]
    r"""Time taken for generation in milliseconds"""
    http_referer: Nullable[str]
    r"""Referer header from the request"""
    id: str
    r"""Unique identifier for the generation"""
    is_byok: bool
    r"""Whether this used bring-your-own-key"""
    latency: Nullable[float]
    r"""Total latency in milliseconds"""
    model: str
    r"""Model used for the generation"""
    moderation_latency: Nullable[float]
    r"""Moderation latency in milliseconds"""
    native_finish_reason: Nullable[str]
    r"""Native finish reason as reported by provider"""
    native_tokens_cached: Nullable[int]
    r"""Native cached tokens as reported by provider"""
    native_tokens_completion: Nullable[int]
    r"""Native completion tokens as reported by provider"""
    native_tokens_completion_images: Nullable[int]
    r"""Native completion image tokens as reported by provider"""
    native_tokens_prompt: Nullable[int]
    r"""Native prompt tokens as reported by provider"""
    native_tokens_reasoning: Nullable[int]
    r"""Native reasoning tokens as reported by provider"""
    num_fetches: Nullable[int]
    r"""Number of web fetches performed"""
    num_input_audio_prompt: Nullable[int]
    r"""Number of audio inputs in the prompt"""
    num_media_completion: Nullable[int]
    r"""Number of media items in the completion"""
    num_media_prompt: Nullable[int]
    r"""Number of media items in the prompt"""
    num_search_results: Nullable[int]
    r"""Number of search results included"""
    origin: str
    r"""Origin URL of the request"""
    preset_id: Nullable[str]
    r"""ID of the preset used for this generation, null if no preset was used"""
    provider_name: Nullable[str]
    r"""Name of the provider that served the request"""
    provider_responses: Nullable[List[ProviderResponseTypedDict]]
    r"""List of provider responses for this generation, including fallback attempts"""
    router: Nullable[str]
    r"""Router used for the request (e.g., openrouter/auto)"""
    service_tier: Nullable[str]
    r"""Service tier the upstream provider reported running this request on, or null if it did not report one."""
    streamed: Nullable[bool]
    r"""Whether the response was streamed"""
    tokens_completion: Nullable[int]
    r"""Number of tokens in the completion"""
    tokens_prompt: Nullable[int]
    r"""Number of tokens in the prompt"""
    total_cost: float
    r"""Total cost of the generation in USD"""
    upstream_id: Nullable[str]
    r"""Upstream provider's identifier for this generation"""
    upstream_inference_cost: Nullable[float]
    r"""Cost charged by the upstream provider"""
    usage: float
    r"""Usage amount in USD"""
    user_agent: Nullable[str]
    r"""User-Agent header from the request"""
    web_search_engine: Nullable[str]
    r"""The resolved web search engine used for this generation (e.g. exa, firecrawl, parallel)"""
    request_id: NotRequired[Nullable[str]]
    r"""Unique identifier grouping all generations from a single API request"""
    response_cache_source_id: NotRequired[Nullable[str]]
    r"""If this generation was served from response cache, contains the original generation ID. Null otherwise."""
    session_id: NotRequired[Nullable[str]]
    r"""Session identifier grouping multiple generations in the same session"""


class GenerationResponseData(BaseModel):
    r"""Generation data"""

    api_type: Nullable[APIType]
    r"""Type of API used for the generation"""

    app_id: Nullable[int]
    r"""ID of the app that made the request"""

    cache_discount: Nullable[float]
    r"""Discount applied due to caching"""

    cancelled: Nullable[bool]
    r"""Whether the generation was cancelled"""

    created_at: str
    r"""ISO 8601 timestamp of when the generation was created"""

    data_region: DataRegion
    r"""The data region this generation was routed through. 'europe' for EU-routed requests, 'global' otherwise."""

    external_user: Nullable[str]
    r"""External user identifier"""

    finish_reason: Nullable[str]
    r"""Reason the generation finished"""

    generation_time: Nullable[float]
    r"""Time taken for generation in milliseconds"""

    http_referer: Nullable[str]
    r"""Referer header from the request"""

    id: str
    r"""Unique identifier for the generation"""

    is_byok: bool
    r"""Whether this used bring-your-own-key"""

    latency: Nullable[float]
    r"""Total latency in milliseconds"""

    model: str
    r"""Model used for the generation"""

    moderation_latency: Nullable[float]
    r"""Moderation latency in milliseconds"""

    native_finish_reason: Nullable[str]
    r"""Native finish reason as reported by provider"""

    native_tokens_cached: Nullable[int]
    r"""Native cached tokens as reported by provider"""

    native_tokens_completion: Nullable[int]
    r"""Native completion tokens as reported by provider"""

    native_tokens_completion_images: Nullable[int]
    r"""Native completion image tokens as reported by provider"""

    native_tokens_prompt: Nullable[int]
    r"""Native prompt tokens as reported by provider"""

    native_tokens_reasoning: Nullable[int]
    r"""Native reasoning tokens as reported by provider"""

    num_fetches: Nullable[int]
    r"""Number of web fetches performed"""

    num_input_audio_prompt: Nullable[int]
    r"""Number of audio inputs in the prompt"""

    num_media_completion: Nullable[int]
    r"""Number of media items in the completion"""

    num_media_prompt: Nullable[int]
    r"""Number of media items in the prompt"""

    num_search_results: Nullable[int]
    r"""Number of search results included"""

    origin: str
    r"""Origin URL of the request"""

    preset_id: Nullable[str]
    r"""ID of the preset used for this generation, null if no preset was used"""

    provider_name: Nullable[str]
    r"""Name of the provider that served the request"""

    provider_responses: Nullable[List[ProviderResponse]]
    r"""List of provider responses for this generation, including fallback attempts"""

    router: Nullable[str]
    r"""Router used for the request (e.g., openrouter/auto)"""

    service_tier: Nullable[str]
    r"""Service tier the upstream provider reported running this request on, or null if it did not report one."""

    streamed: Nullable[bool]
    r"""Whether the response was streamed"""

    tokens_completion: Nullable[int]
    r"""Number of tokens in the completion"""

    tokens_prompt: Nullable[int]
    r"""Number of tokens in the prompt"""

    total_cost: float
    r"""Total cost of the generation in USD"""

    upstream_id: Nullable[str]
    r"""Upstream provider's identifier for this generation"""

    upstream_inference_cost: Nullable[float]
    r"""Cost charged by the upstream provider"""

    usage: float
    r"""Usage amount in USD"""

    user_agent: Nullable[str]
    r"""User-Agent header from the request"""

    web_search_engine: Nullable[str]
    r"""The resolved web search engine used for this generation (e.g. exa, firecrawl, parallel)"""

    request_id: OptionalNullable[str] = UNSET
    r"""Unique identifier grouping all generations from a single API request"""

    response_cache_source_id: OptionalNullable[str] = UNSET
    r"""If this generation was served from response cache, contains the original generation ID. Null otherwise."""

    session_id: OptionalNullable[str] = UNSET
    r"""Session identifier grouping multiple generations in the same session"""

    @model_serializer(mode="wrap")
    def serialize_model(self, handler):
        optional_fields = set(["request_id", "response_cache_source_id", "session_id"])
        nullable_fields = set(
            [
                "api_type",
                "app_id",
                "cache_discount",
                "cancelled",
                "external_user",
                "finish_reason",
                "generation_time",
                "http_referer",
                "latency",
                "moderation_latency",
                "native_finish_reason",
                "native_tokens_cached",
                "native_tokens_completion",
                "native_tokens_completion_images",
                "native_tokens_prompt",
                "native_tokens_reasoning",
                "num_fetches",
                "num_input_audio_prompt",
                "num_media_completion",
                "num_media_prompt",
                "num_search_results",
                "preset_id",
                "provider_name",
                "provider_responses",
                "request_id",
                "response_cache_source_id",
                "router",
                "service_tier",
                "session_id",
                "streamed",
                "tokens_completion",
                "tokens_prompt",
                "upstream_id",
                "upstream_inference_cost",
                "user_agent",
                "web_search_engine",
            ]
        )
        serialized = handler(self)
        m = {}

        for n, f in type(self).model_fields.items():
            k = f.alias or n
            val = serialized.get(k, serialized.get(n))
            is_nullable_and_explicitly_set = (
                k in nullable_fields
                and (self.__pydantic_fields_set__.intersection({n}))  # pylint: disable=no-member
            )

            if val != UNSET_SENTINEL:
                if (
                    val is not None
                    or k not in optional_fields
                    or is_nullable_and_explicitly_set
                ):
                    m[k] = val

        return m


class GenerationResponseTypedDict(TypedDict):
    r"""Generation response"""

    data: GenerationResponseDataTypedDict
    r"""Generation data"""


class GenerationResponse(BaseModel):
    r"""Generation response"""

    data: GenerationResponseData
    r"""Generation data"""