mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
fix: update OpenAPI spec with router field (#32)
This commit is contained in:
Matt Apperson
@@ -38,8 +38,12 @@ if TYPE_CHECKING:
|
||||
from .chatgenerationparams import (
|
||||
ChatGenerationParams,
|
||||
ChatGenerationParamsDataCollection,
|
||||
ChatGenerationParamsImageConfig,
|
||||
ChatGenerationParamsImageConfigTypedDict,
|
||||
ChatGenerationParamsMaxPrice,
|
||||
ChatGenerationParamsMaxPriceTypedDict,
|
||||
ChatGenerationParamsPluginAutoRouter,
|
||||
ChatGenerationParamsPluginAutoRouterTypedDict,
|
||||
ChatGenerationParamsPluginFileParser,
|
||||
ChatGenerationParamsPluginFileParserTypedDict,
|
||||
ChatGenerationParamsPluginModeration,
|
||||
@@ -50,6 +54,14 @@ if TYPE_CHECKING:
|
||||
ChatGenerationParamsPluginUnionTypedDict,
|
||||
ChatGenerationParamsPluginWeb,
|
||||
ChatGenerationParamsPluginWebTypedDict,
|
||||
ChatGenerationParamsPreferredMaxLatency,
|
||||
ChatGenerationParamsPreferredMaxLatencyTypedDict,
|
||||
ChatGenerationParamsPreferredMaxLatencyUnion,
|
||||
ChatGenerationParamsPreferredMaxLatencyUnionTypedDict,
|
||||
ChatGenerationParamsPreferredMinThroughput,
|
||||
ChatGenerationParamsPreferredMinThroughputTypedDict,
|
||||
ChatGenerationParamsPreferredMinThroughputUnion,
|
||||
ChatGenerationParamsPreferredMinThroughputUnionTypedDict,
|
||||
ChatGenerationParamsProvider,
|
||||
ChatGenerationParamsProviderTypedDict,
|
||||
ChatGenerationParamsResponseFormatJSONObject,
|
||||
@@ -67,6 +79,7 @@ if TYPE_CHECKING:
|
||||
DebugTypedDict,
|
||||
Effort,
|
||||
Engine,
|
||||
Modality,
|
||||
Pdf,
|
||||
PdfEngine,
|
||||
PdfTypedDict,
|
||||
@@ -123,9 +136,9 @@ if TYPE_CHECKING:
|
||||
)
|
||||
from .chatmessagetokenlogprob import (
|
||||
ChatMessageTokenLogprob,
|
||||
ChatMessageTokenLogprobTopLogprob,
|
||||
ChatMessageTokenLogprobTopLogprobTypedDict,
|
||||
ChatMessageTokenLogprobTypedDict,
|
||||
TopLogprob,
|
||||
TopLogprobTypedDict,
|
||||
)
|
||||
from .chatmessagetokenlogprobs import (
|
||||
ChatMessageTokenLogprobs,
|
||||
@@ -333,17 +346,21 @@ if TYPE_CHECKING:
|
||||
from .openairesponsestruncation import OpenAIResponsesTruncation
|
||||
from .openresponseseasyinputmessage import (
|
||||
OpenResponsesEasyInputMessage,
|
||||
OpenResponsesEasyInputMessageContent1,
|
||||
OpenResponsesEasyInputMessageContent1TypedDict,
|
||||
OpenResponsesEasyInputMessageContent2,
|
||||
OpenResponsesEasyInputMessageContent2TypedDict,
|
||||
OpenResponsesEasyInputMessageContentInputImage,
|
||||
OpenResponsesEasyInputMessageContentInputImageTypedDict,
|
||||
OpenResponsesEasyInputMessageContentType,
|
||||
OpenResponsesEasyInputMessageContentUnion1,
|
||||
OpenResponsesEasyInputMessageContentUnion1TypedDict,
|
||||
OpenResponsesEasyInputMessageContentUnion2,
|
||||
OpenResponsesEasyInputMessageContentUnion2TypedDict,
|
||||
OpenResponsesEasyInputMessageDetail,
|
||||
OpenResponsesEasyInputMessageRoleAssistant,
|
||||
OpenResponsesEasyInputMessageRoleDeveloper,
|
||||
OpenResponsesEasyInputMessageRoleSystem,
|
||||
OpenResponsesEasyInputMessageRoleUnion,
|
||||
OpenResponsesEasyInputMessageRoleUnionTypedDict,
|
||||
OpenResponsesEasyInputMessageRoleUser,
|
||||
OpenResponsesEasyInputMessageType,
|
||||
OpenResponsesEasyInputMessageTypeMessage,
|
||||
OpenResponsesEasyInputMessageTypedDict,
|
||||
)
|
||||
from .openresponseserrorevent import (
|
||||
@@ -389,14 +406,18 @@ if TYPE_CHECKING:
|
||||
)
|
||||
from .openresponsesinputmessageitem import (
|
||||
OpenResponsesInputMessageItem,
|
||||
OpenResponsesInputMessageItemContent,
|
||||
OpenResponsesInputMessageItemContentTypedDict,
|
||||
OpenResponsesInputMessageItemContentInputImage,
|
||||
OpenResponsesInputMessageItemContentInputImageTypedDict,
|
||||
OpenResponsesInputMessageItemContentType,
|
||||
OpenResponsesInputMessageItemContentUnion,
|
||||
OpenResponsesInputMessageItemContentUnionTypedDict,
|
||||
OpenResponsesInputMessageItemDetail,
|
||||
OpenResponsesInputMessageItemRoleDeveloper,
|
||||
OpenResponsesInputMessageItemRoleSystem,
|
||||
OpenResponsesInputMessageItemRoleUnion,
|
||||
OpenResponsesInputMessageItemRoleUnionTypedDict,
|
||||
OpenResponsesInputMessageItemRoleUser,
|
||||
OpenResponsesInputMessageItemType,
|
||||
OpenResponsesInputMessageItemTypeMessage,
|
||||
OpenResponsesInputMessageItemTypedDict,
|
||||
)
|
||||
from .openresponseslogprobs import (
|
||||
@@ -454,6 +475,7 @@ if TYPE_CHECKING:
|
||||
OpenResponsesReasoningSummaryTextDoneEventTypedDict,
|
||||
)
|
||||
from .openresponsesrequest import (
|
||||
IDAutoRouter,
|
||||
IDFileParser,
|
||||
IDModeration,
|
||||
IDResponseHealing,
|
||||
@@ -461,12 +483,16 @@ if TYPE_CHECKING:
|
||||
OpenResponsesRequest,
|
||||
OpenResponsesRequestIgnore,
|
||||
OpenResponsesRequestIgnoreTypedDict,
|
||||
OpenResponsesRequestImageConfig,
|
||||
OpenResponsesRequestImageConfigTypedDict,
|
||||
OpenResponsesRequestMaxPrice,
|
||||
OpenResponsesRequestMaxPriceTypedDict,
|
||||
OpenResponsesRequestOnly,
|
||||
OpenResponsesRequestOnlyTypedDict,
|
||||
OpenResponsesRequestOrder,
|
||||
OpenResponsesRequestOrderTypedDict,
|
||||
OpenResponsesRequestPluginAutoRouter,
|
||||
OpenResponsesRequestPluginAutoRouterTypedDict,
|
||||
OpenResponsesRequestPluginFileParser,
|
||||
OpenResponsesRequestPluginFileParserTypedDict,
|
||||
OpenResponsesRequestPluginModeration,
|
||||
@@ -622,7 +648,21 @@ if TYPE_CHECKING:
|
||||
)
|
||||
from .pdfparserengine import PDFParserEngine
|
||||
from .pdfparseroptions import PDFParserOptions, PDFParserOptionsTypedDict
|
||||
from .percentilelatencycutoffs import (
|
||||
PercentileLatencyCutoffs,
|
||||
PercentileLatencyCutoffsTypedDict,
|
||||
)
|
||||
from .percentilestats import PercentileStats, PercentileStatsTypedDict
|
||||
from .percentilethroughputcutoffs import (
|
||||
PercentileThroughputCutoffs,
|
||||
PercentileThroughputCutoffsTypedDict,
|
||||
)
|
||||
from .perrequestlimits import PerRequestLimits, PerRequestLimitsTypedDict
|
||||
from .preferredmaxlatency import PreferredMaxLatency, PreferredMaxLatencyTypedDict
|
||||
from .preferredminthroughput import (
|
||||
PreferredMinThroughput,
|
||||
PreferredMinThroughputTypedDict,
|
||||
)
|
||||
from .providername import ProviderName
|
||||
from .provideroverloadedresponseerrordata import (
|
||||
ProviderOverloadedResponseErrorData,
|
||||
@@ -717,8 +757,17 @@ if TYPE_CHECKING:
|
||||
ResponseInputTextType,
|
||||
ResponseInputTextTypedDict,
|
||||
)
|
||||
from .responseinputvideo import (
|
||||
ResponseInputVideo,
|
||||
ResponseInputVideoType,
|
||||
ResponseInputVideoTypedDict,
|
||||
)
|
||||
from .responseoutputtext import (
|
||||
Logprob,
|
||||
LogprobTypedDict,
|
||||
ResponseOutputText,
|
||||
ResponseOutputTextTopLogprob,
|
||||
ResponseOutputTextTopLogprobTypedDict,
|
||||
ResponseOutputTextType,
|
||||
ResponseOutputTextTypedDict,
|
||||
)
|
||||
@@ -765,6 +814,7 @@ if TYPE_CHECKING:
|
||||
)
|
||||
from .responsesoutputitemreasoning import (
|
||||
ResponsesOutputItemReasoning,
|
||||
ResponsesOutputItemReasoningFormat,
|
||||
ResponsesOutputItemReasoningStatusCompleted,
|
||||
ResponsesOutputItemReasoningStatusInProgress,
|
||||
ResponsesOutputItemReasoningStatusIncomplete,
|
||||
@@ -786,6 +836,7 @@ if TYPE_CHECKING:
|
||||
ResponsesOutputMessageType,
|
||||
ResponsesOutputMessageTypedDict,
|
||||
)
|
||||
from .responsesoutputmodality import ResponsesOutputModality
|
||||
from .responsessearchcontextsize import ResponsesSearchContextSize
|
||||
from .responseswebsearchcalloutput import (
|
||||
ResponsesWebSearchCallOutput,
|
||||
@@ -873,8 +924,12 @@ __all__ = [
|
||||
"ChatErrorErrorTypedDict",
|
||||
"ChatGenerationParams",
|
||||
"ChatGenerationParamsDataCollection",
|
||||
"ChatGenerationParamsImageConfig",
|
||||
"ChatGenerationParamsImageConfigTypedDict",
|
||||
"ChatGenerationParamsMaxPrice",
|
||||
"ChatGenerationParamsMaxPriceTypedDict",
|
||||
"ChatGenerationParamsPluginAutoRouter",
|
||||
"ChatGenerationParamsPluginAutoRouterTypedDict",
|
||||
"ChatGenerationParamsPluginFileParser",
|
||||
"ChatGenerationParamsPluginFileParserTypedDict",
|
||||
"ChatGenerationParamsPluginModeration",
|
||||
@@ -885,6 +940,14 @@ __all__ = [
|
||||
"ChatGenerationParamsPluginUnionTypedDict",
|
||||
"ChatGenerationParamsPluginWeb",
|
||||
"ChatGenerationParamsPluginWebTypedDict",
|
||||
"ChatGenerationParamsPreferredMaxLatency",
|
||||
"ChatGenerationParamsPreferredMaxLatencyTypedDict",
|
||||
"ChatGenerationParamsPreferredMaxLatencyUnion",
|
||||
"ChatGenerationParamsPreferredMaxLatencyUnionTypedDict",
|
||||
"ChatGenerationParamsPreferredMinThroughput",
|
||||
"ChatGenerationParamsPreferredMinThroughputTypedDict",
|
||||
"ChatGenerationParamsPreferredMinThroughputUnion",
|
||||
"ChatGenerationParamsPreferredMinThroughputUnionTypedDict",
|
||||
"ChatGenerationParamsProvider",
|
||||
"ChatGenerationParamsProviderTypedDict",
|
||||
"ChatGenerationParamsResponseFormatJSONObject",
|
||||
@@ -920,6 +983,8 @@ __all__ = [
|
||||
"ChatMessageContentItemVideoVideoURL",
|
||||
"ChatMessageContentItemVideoVideoURLTypedDict",
|
||||
"ChatMessageTokenLogprob",
|
||||
"ChatMessageTokenLogprobTopLogprob",
|
||||
"ChatMessageTokenLogprobTopLogprobTypedDict",
|
||||
"ChatMessageTokenLogprobTypedDict",
|
||||
"ChatMessageTokenLogprobs",
|
||||
"ChatMessageTokenLogprobsTypedDict",
|
||||
@@ -996,6 +1061,7 @@ __all__ = [
|
||||
"FilePathTypedDict",
|
||||
"ForbiddenResponseErrorData",
|
||||
"ForbiddenResponseErrorDataTypedDict",
|
||||
"IDAutoRouter",
|
||||
"IDFileParser",
|
||||
"IDModeration",
|
||||
"IDResponseHealing",
|
||||
@@ -1013,12 +1079,15 @@ __all__ = [
|
||||
"JSONSchemaConfigTypedDict",
|
||||
"ListEndpointsResponse",
|
||||
"ListEndpointsResponseTypedDict",
|
||||
"Logprob",
|
||||
"LogprobTypedDict",
|
||||
"Message",
|
||||
"MessageContent",
|
||||
"MessageContentTypedDict",
|
||||
"MessageDeveloper",
|
||||
"MessageDeveloperTypedDict",
|
||||
"MessageTypedDict",
|
||||
"Modality",
|
||||
"Model",
|
||||
"ModelArchitecture",
|
||||
"ModelArchitectureInstructType",
|
||||
@@ -1100,17 +1169,21 @@ __all__ = [
|
||||
"OpenAIResponsesToolChoiceUnionTypedDict",
|
||||
"OpenAIResponsesTruncation",
|
||||
"OpenResponsesEasyInputMessage",
|
||||
"OpenResponsesEasyInputMessageContent1",
|
||||
"OpenResponsesEasyInputMessageContent1TypedDict",
|
||||
"OpenResponsesEasyInputMessageContent2",
|
||||
"OpenResponsesEasyInputMessageContent2TypedDict",
|
||||
"OpenResponsesEasyInputMessageContentInputImage",
|
||||
"OpenResponsesEasyInputMessageContentInputImageTypedDict",
|
||||
"OpenResponsesEasyInputMessageContentType",
|
||||
"OpenResponsesEasyInputMessageContentUnion1",
|
||||
"OpenResponsesEasyInputMessageContentUnion1TypedDict",
|
||||
"OpenResponsesEasyInputMessageContentUnion2",
|
||||
"OpenResponsesEasyInputMessageContentUnion2TypedDict",
|
||||
"OpenResponsesEasyInputMessageDetail",
|
||||
"OpenResponsesEasyInputMessageRoleAssistant",
|
||||
"OpenResponsesEasyInputMessageRoleDeveloper",
|
||||
"OpenResponsesEasyInputMessageRoleSystem",
|
||||
"OpenResponsesEasyInputMessageRoleUnion",
|
||||
"OpenResponsesEasyInputMessageRoleUnionTypedDict",
|
||||
"OpenResponsesEasyInputMessageRoleUser",
|
||||
"OpenResponsesEasyInputMessageType",
|
||||
"OpenResponsesEasyInputMessageTypeMessage",
|
||||
"OpenResponsesEasyInputMessageTypedDict",
|
||||
"OpenResponsesErrorEvent",
|
||||
"OpenResponsesErrorEventType",
|
||||
@@ -1137,14 +1210,18 @@ __all__ = [
|
||||
"OpenResponsesInput1",
|
||||
"OpenResponsesInput1TypedDict",
|
||||
"OpenResponsesInputMessageItem",
|
||||
"OpenResponsesInputMessageItemContent",
|
||||
"OpenResponsesInputMessageItemContentTypedDict",
|
||||
"OpenResponsesInputMessageItemContentInputImage",
|
||||
"OpenResponsesInputMessageItemContentInputImageTypedDict",
|
||||
"OpenResponsesInputMessageItemContentType",
|
||||
"OpenResponsesInputMessageItemContentUnion",
|
||||
"OpenResponsesInputMessageItemContentUnionTypedDict",
|
||||
"OpenResponsesInputMessageItemDetail",
|
||||
"OpenResponsesInputMessageItemRoleDeveloper",
|
||||
"OpenResponsesInputMessageItemRoleSystem",
|
||||
"OpenResponsesInputMessageItemRoleUnion",
|
||||
"OpenResponsesInputMessageItemRoleUnionTypedDict",
|
||||
"OpenResponsesInputMessageItemRoleUser",
|
||||
"OpenResponsesInputMessageItemType",
|
||||
"OpenResponsesInputMessageItemTypeMessage",
|
||||
"OpenResponsesInputMessageItemTypedDict",
|
||||
"OpenResponsesInputTypedDict",
|
||||
"OpenResponsesLogProbs",
|
||||
@@ -1185,12 +1262,16 @@ __all__ = [
|
||||
"OpenResponsesRequest",
|
||||
"OpenResponsesRequestIgnore",
|
||||
"OpenResponsesRequestIgnoreTypedDict",
|
||||
"OpenResponsesRequestImageConfig",
|
||||
"OpenResponsesRequestImageConfigTypedDict",
|
||||
"OpenResponsesRequestMaxPrice",
|
||||
"OpenResponsesRequestMaxPriceTypedDict",
|
||||
"OpenResponsesRequestOnly",
|
||||
"OpenResponsesRequestOnlyTypedDict",
|
||||
"OpenResponsesRequestOrder",
|
||||
"OpenResponsesRequestOrderTypedDict",
|
||||
"OpenResponsesRequestPluginAutoRouter",
|
||||
"OpenResponsesRequestPluginAutoRouterTypedDict",
|
||||
"OpenResponsesRequestPluginFileParser",
|
||||
"OpenResponsesRequestPluginFileParserTypedDict",
|
||||
"OpenResponsesRequestPluginModeration",
|
||||
@@ -1305,6 +1386,16 @@ __all__ = [
|
||||
"PdfTypedDict",
|
||||
"PerRequestLimits",
|
||||
"PerRequestLimitsTypedDict",
|
||||
"PercentileLatencyCutoffs",
|
||||
"PercentileLatencyCutoffsTypedDict",
|
||||
"PercentileStats",
|
||||
"PercentileStatsTypedDict",
|
||||
"PercentileThroughputCutoffs",
|
||||
"PercentileThroughputCutoffsTypedDict",
|
||||
"PreferredMaxLatency",
|
||||
"PreferredMaxLatencyTypedDict",
|
||||
"PreferredMinThroughput",
|
||||
"PreferredMinThroughputTypedDict",
|
||||
"Pricing",
|
||||
"PricingTypedDict",
|
||||
"Prompt",
|
||||
@@ -1379,7 +1470,12 @@ __all__ = [
|
||||
"ResponseInputText",
|
||||
"ResponseInputTextType",
|
||||
"ResponseInputTextTypedDict",
|
||||
"ResponseInputVideo",
|
||||
"ResponseInputVideoType",
|
||||
"ResponseInputVideoTypedDict",
|
||||
"ResponseOutputText",
|
||||
"ResponseOutputTextTopLogprob",
|
||||
"ResponseOutputTextTopLogprobTypedDict",
|
||||
"ResponseOutputTextType",
|
||||
"ResponseOutputTextTypedDict",
|
||||
"ResponseTextConfig",
|
||||
@@ -1412,6 +1508,7 @@ __all__ = [
|
||||
"ResponsesOutputItemFunctionCallType",
|
||||
"ResponsesOutputItemFunctionCallTypedDict",
|
||||
"ResponsesOutputItemReasoning",
|
||||
"ResponsesOutputItemReasoningFormat",
|
||||
"ResponsesOutputItemReasoningStatusCompleted",
|
||||
"ResponsesOutputItemReasoningStatusInProgress",
|
||||
"ResponsesOutputItemReasoningStatusIncomplete",
|
||||
@@ -1431,6 +1528,7 @@ __all__ = [
|
||||
"ResponsesOutputMessageStatusUnionTypedDict",
|
||||
"ResponsesOutputMessageType",
|
||||
"ResponsesOutputMessageTypedDict",
|
||||
"ResponsesOutputModality",
|
||||
"ResponsesSearchContextSize",
|
||||
"ResponsesWebSearchCallOutput",
|
||||
"ResponsesWebSearchCallOutputType",
|
||||
@@ -1476,8 +1574,6 @@ __all__ = [
|
||||
"ToolResponseMessageContent",
|
||||
"ToolResponseMessageContentTypedDict",
|
||||
"ToolResponseMessageTypedDict",
|
||||
"TopLogprob",
|
||||
"TopLogprobTypedDict",
|
||||
"TopProviderInfo",
|
||||
"TopProviderInfoTypedDict",
|
||||
"Truncation",
|
||||
@@ -1554,8 +1650,12 @@ _dynamic_imports: dict[str, str] = {
|
||||
"CodeTypedDict": ".chaterror",
|
||||
"ChatGenerationParams": ".chatgenerationparams",
|
||||
"ChatGenerationParamsDataCollection": ".chatgenerationparams",
|
||||
"ChatGenerationParamsImageConfig": ".chatgenerationparams",
|
||||
"ChatGenerationParamsImageConfigTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsMaxPrice": ".chatgenerationparams",
|
||||
"ChatGenerationParamsMaxPriceTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginAutoRouter": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginAutoRouterTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginFileParser": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginFileParserTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginModeration": ".chatgenerationparams",
|
||||
@@ -1566,6 +1666,14 @@ _dynamic_imports: dict[str, str] = {
|
||||
"ChatGenerationParamsPluginUnionTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginWeb": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPluginWebTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMaxLatency": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMaxLatencyTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMaxLatencyUnion": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMaxLatencyUnionTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMinThroughput": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMinThroughputTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMinThroughputUnion": ".chatgenerationparams",
|
||||
"ChatGenerationParamsPreferredMinThroughputUnionTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsProvider": ".chatgenerationparams",
|
||||
"ChatGenerationParamsProviderTypedDict": ".chatgenerationparams",
|
||||
"ChatGenerationParamsResponseFormatJSONObject": ".chatgenerationparams",
|
||||
@@ -1583,6 +1691,7 @@ _dynamic_imports: dict[str, str] = {
|
||||
"DebugTypedDict": ".chatgenerationparams",
|
||||
"Effort": ".chatgenerationparams",
|
||||
"Engine": ".chatgenerationparams",
|
||||
"Modality": ".chatgenerationparams",
|
||||
"Pdf": ".chatgenerationparams",
|
||||
"PdfEngine": ".chatgenerationparams",
|
||||
"PdfTypedDict": ".chatgenerationparams",
|
||||
@@ -1623,9 +1732,9 @@ _dynamic_imports: dict[str, str] = {
|
||||
"VideoURL2": ".chatmessagecontentitemvideo",
|
||||
"VideoURL2TypedDict": ".chatmessagecontentitemvideo",
|
||||
"ChatMessageTokenLogprob": ".chatmessagetokenlogprob",
|
||||
"ChatMessageTokenLogprobTopLogprob": ".chatmessagetokenlogprob",
|
||||
"ChatMessageTokenLogprobTopLogprobTypedDict": ".chatmessagetokenlogprob",
|
||||
"ChatMessageTokenLogprobTypedDict": ".chatmessagetokenlogprob",
|
||||
"TopLogprob": ".chatmessagetokenlogprob",
|
||||
"TopLogprobTypedDict": ".chatmessagetokenlogprob",
|
||||
"ChatMessageTokenLogprobs": ".chatmessagetokenlogprobs",
|
||||
"ChatMessageTokenLogprobsTypedDict": ".chatmessagetokenlogprobs",
|
||||
"ChatMessageToolCall": ".chatmessagetoolcall",
|
||||
@@ -1798,17 +1907,21 @@ _dynamic_imports: dict[str, str] = {
|
||||
"TypeTypedDict": ".openairesponsestoolchoice_union",
|
||||
"OpenAIResponsesTruncation": ".openairesponsestruncation",
|
||||
"OpenResponsesEasyInputMessage": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContent1": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContent1TypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContent2": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContent2TypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentInputImage": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentInputImageTypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentType": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentUnion1": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentUnion1TypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentUnion2": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageContentUnion2TypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageDetail": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageRoleAssistant": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageRoleDeveloper": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageRoleSystem": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageRoleUnion": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageRoleUnionTypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageRoleUser": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageType": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageTypeMessage": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesEasyInputMessageTypedDict": ".openresponseseasyinputmessage",
|
||||
"OpenResponsesErrorEvent": ".openresponseserrorevent",
|
||||
"OpenResponsesErrorEventType": ".openresponseserrorevent",
|
||||
@@ -1836,14 +1949,18 @@ _dynamic_imports: dict[str, str] = {
|
||||
"OpenResponsesInput1TypedDict": ".openresponsesinput",
|
||||
"OpenResponsesInputTypedDict": ".openresponsesinput",
|
||||
"OpenResponsesInputMessageItem": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContent": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContentTypedDict": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContentInputImage": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContentInputImageTypedDict": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContentType": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContentUnion": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemContentUnionTypedDict": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemDetail": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemRoleDeveloper": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemRoleSystem": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemRoleUnion": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemRoleUnionTypedDict": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemRoleUser": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemType": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemTypeMessage": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesInputMessageItemTypedDict": ".openresponsesinputmessageitem",
|
||||
"OpenResponsesLogProbs": ".openresponseslogprobs",
|
||||
"OpenResponsesLogProbsTypedDict": ".openresponseslogprobs",
|
||||
@@ -1881,6 +1998,7 @@ _dynamic_imports: dict[str, str] = {
|
||||
"OpenResponsesReasoningSummaryTextDoneEvent": ".openresponsesreasoningsummarytextdoneevent",
|
||||
"OpenResponsesReasoningSummaryTextDoneEventType": ".openresponsesreasoningsummarytextdoneevent",
|
||||
"OpenResponsesReasoningSummaryTextDoneEventTypedDict": ".openresponsesreasoningsummarytextdoneevent",
|
||||
"IDAutoRouter": ".openresponsesrequest",
|
||||
"IDFileParser": ".openresponsesrequest",
|
||||
"IDModeration": ".openresponsesrequest",
|
||||
"IDResponseHealing": ".openresponsesrequest",
|
||||
@@ -1888,12 +2006,16 @@ _dynamic_imports: dict[str, str] = {
|
||||
"OpenResponsesRequest": ".openresponsesrequest",
|
||||
"OpenResponsesRequestIgnore": ".openresponsesrequest",
|
||||
"OpenResponsesRequestIgnoreTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestImageConfig": ".openresponsesrequest",
|
||||
"OpenResponsesRequestImageConfigTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestMaxPrice": ".openresponsesrequest",
|
||||
"OpenResponsesRequestMaxPriceTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestOnly": ".openresponsesrequest",
|
||||
"OpenResponsesRequestOnlyTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestOrder": ".openresponsesrequest",
|
||||
"OpenResponsesRequestOrderTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestPluginAutoRouter": ".openresponsesrequest",
|
||||
"OpenResponsesRequestPluginAutoRouterTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestPluginFileParser": ".openresponsesrequest",
|
||||
"OpenResponsesRequestPluginFileParserTypedDict": ".openresponsesrequest",
|
||||
"OpenResponsesRequestPluginModeration": ".openresponsesrequest",
|
||||
@@ -2025,8 +2147,18 @@ _dynamic_imports: dict[str, str] = {
|
||||
"PDFParserEngine": ".pdfparserengine",
|
||||
"PDFParserOptions": ".pdfparseroptions",
|
||||
"PDFParserOptionsTypedDict": ".pdfparseroptions",
|
||||
"PercentileLatencyCutoffs": ".percentilelatencycutoffs",
|
||||
"PercentileLatencyCutoffsTypedDict": ".percentilelatencycutoffs",
|
||||
"PercentileStats": ".percentilestats",
|
||||
"PercentileStatsTypedDict": ".percentilestats",
|
||||
"PercentileThroughputCutoffs": ".percentilethroughputcutoffs",
|
||||
"PercentileThroughputCutoffsTypedDict": ".percentilethroughputcutoffs",
|
||||
"PerRequestLimits": ".perrequestlimits",
|
||||
"PerRequestLimitsTypedDict": ".perrequestlimits",
|
||||
"PreferredMaxLatency": ".preferredmaxlatency",
|
||||
"PreferredMaxLatencyTypedDict": ".preferredmaxlatency",
|
||||
"PreferredMinThroughput": ".preferredminthroughput",
|
||||
"PreferredMinThroughputTypedDict": ".preferredminthroughput",
|
||||
"ProviderName": ".providername",
|
||||
"ProviderOverloadedResponseErrorData": ".provideroverloadedresponseerrordata",
|
||||
"ProviderOverloadedResponseErrorDataTypedDict": ".provideroverloadedresponseerrordata",
|
||||
@@ -2095,7 +2227,14 @@ _dynamic_imports: dict[str, str] = {
|
||||
"ResponseInputText": ".responseinputtext",
|
||||
"ResponseInputTextType": ".responseinputtext",
|
||||
"ResponseInputTextTypedDict": ".responseinputtext",
|
||||
"ResponseInputVideo": ".responseinputvideo",
|
||||
"ResponseInputVideoType": ".responseinputvideo",
|
||||
"ResponseInputVideoTypedDict": ".responseinputvideo",
|
||||
"Logprob": ".responseoutputtext",
|
||||
"LogprobTypedDict": ".responseoutputtext",
|
||||
"ResponseOutputText": ".responseoutputtext",
|
||||
"ResponseOutputTextTopLogprob": ".responseoutputtext",
|
||||
"ResponseOutputTextTopLogprobTypedDict": ".responseoutputtext",
|
||||
"ResponseOutputTextType": ".responseoutputtext",
|
||||
"ResponseOutputTextTypedDict": ".responseoutputtext",
|
||||
"CodeEnum": ".responseserrorfield",
|
||||
@@ -2127,6 +2266,7 @@ _dynamic_imports: dict[str, str] = {
|
||||
"ResponsesOutputItemFunctionCallType": ".responsesoutputitemfunctioncall",
|
||||
"ResponsesOutputItemFunctionCallTypedDict": ".responsesoutputitemfunctioncall",
|
||||
"ResponsesOutputItemReasoning": ".responsesoutputitemreasoning",
|
||||
"ResponsesOutputItemReasoningFormat": ".responsesoutputitemreasoning",
|
||||
"ResponsesOutputItemReasoningStatusCompleted": ".responsesoutputitemreasoning",
|
||||
"ResponsesOutputItemReasoningStatusInProgress": ".responsesoutputitemreasoning",
|
||||
"ResponsesOutputItemReasoningStatusIncomplete": ".responsesoutputitemreasoning",
|
||||
@@ -2145,6 +2285,7 @@ _dynamic_imports: dict[str, str] = {
|
||||
"ResponsesOutputMessageStatusUnionTypedDict": ".responsesoutputmessage",
|
||||
"ResponsesOutputMessageType": ".responsesoutputmessage",
|
||||
"ResponsesOutputMessageTypedDict": ".responsesoutputmessage",
|
||||
"ResponsesOutputModality": ".responsesoutputmodality",
|
||||
"ResponsesSearchContextSize": ".responsessearchcontextsize",
|
||||
"ResponsesWebSearchCallOutput": ".responseswebsearchcalloutput",
|
||||
"ResponsesWebSearchCallOutputType": ".responseswebsearchcalloutput",
|
||||
|
||||
@@ -36,12 +36,12 @@ Schema0Enum = Union[
|
||||
"Fireworks",
|
||||
"Friendli",
|
||||
"GMICloud",
|
||||
"GoPomelo",
|
||||
"Google",
|
||||
"Google AI Studio",
|
||||
"Groq",
|
||||
"Hyperbolic",
|
||||
"Inception",
|
||||
"Inceptron",
|
||||
"InferenceNet",
|
||||
"Infermatic",
|
||||
"Inflection",
|
||||
@@ -66,13 +66,14 @@ Schema0Enum = Union[
|
||||
"Phala",
|
||||
"Relace",
|
||||
"SambaNova",
|
||||
"Seed",
|
||||
"SiliconFlow",
|
||||
"Sourceful",
|
||||
"Stealth",
|
||||
"StreamLake",
|
||||
"Switchpoint",
|
||||
"Targon",
|
||||
"Together",
|
||||
"Upstage",
|
||||
"Venice",
|
||||
"WandB",
|
||||
"Xiaomi",
|
||||
|
||||
@@ -21,6 +21,7 @@ Schema5 = Union[
|
||||
Literal[
|
||||
"unknown",
|
||||
"openai-responses-v1",
|
||||
"azure-openai-responses-v1",
|
||||
"xai-responses-v1",
|
||||
"anthropic-claude-v1",
|
||||
"google-gemini-v1",
|
||||
|
||||
@@ -80,6 +80,124 @@ class ChatGenerationParamsMaxPrice(BaseModel):
|
||||
request: Optional[Any] = None
|
||||
|
||||
|
||||
class ChatGenerationParamsPreferredMinThroughputTypedDict(TypedDict):
|
||||
p50: NotRequired[Nullable[float]]
|
||||
p75: NotRequired[Nullable[float]]
|
||||
p90: NotRequired[Nullable[float]]
|
||||
p99: NotRequired[Nullable[float]]
|
||||
|
||||
|
||||
class ChatGenerationParamsPreferredMinThroughput(BaseModel):
|
||||
p50: OptionalNullable[float] = UNSET
|
||||
|
||||
p75: OptionalNullable[float] = UNSET
|
||||
|
||||
p90: OptionalNullable[float] = UNSET
|
||||
|
||||
p99: OptionalNullable[float] = UNSET
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["p50", "p75", "p90", "p99"]
|
||||
nullable_fields = ["p50", "p75", "p90", "p99"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
ChatGenerationParamsPreferredMinThroughputUnionTypedDict = TypeAliasType(
|
||||
"ChatGenerationParamsPreferredMinThroughputUnionTypedDict",
|
||||
Union[ChatGenerationParamsPreferredMinThroughputTypedDict, float],
|
||||
)
|
||||
|
||||
|
||||
ChatGenerationParamsPreferredMinThroughputUnion = TypeAliasType(
|
||||
"ChatGenerationParamsPreferredMinThroughputUnion",
|
||||
Union[ChatGenerationParamsPreferredMinThroughput, float],
|
||||
)
|
||||
|
||||
|
||||
class ChatGenerationParamsPreferredMaxLatencyTypedDict(TypedDict):
|
||||
p50: NotRequired[Nullable[float]]
|
||||
p75: NotRequired[Nullable[float]]
|
||||
p90: NotRequired[Nullable[float]]
|
||||
p99: NotRequired[Nullable[float]]
|
||||
|
||||
|
||||
class ChatGenerationParamsPreferredMaxLatency(BaseModel):
|
||||
p50: OptionalNullable[float] = UNSET
|
||||
|
||||
p75: OptionalNullable[float] = UNSET
|
||||
|
||||
p90: OptionalNullable[float] = UNSET
|
||||
|
||||
p99: OptionalNullable[float] = UNSET
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["p50", "p75", "p90", "p99"]
|
||||
nullable_fields = ["p50", "p75", "p90", "p99"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
ChatGenerationParamsPreferredMaxLatencyUnionTypedDict = TypeAliasType(
|
||||
"ChatGenerationParamsPreferredMaxLatencyUnionTypedDict",
|
||||
Union[ChatGenerationParamsPreferredMaxLatencyTypedDict, float],
|
||||
)
|
||||
|
||||
|
||||
ChatGenerationParamsPreferredMaxLatencyUnion = TypeAliasType(
|
||||
"ChatGenerationParamsPreferredMaxLatencyUnion",
|
||||
Union[ChatGenerationParamsPreferredMaxLatency, float],
|
||||
)
|
||||
|
||||
|
||||
class ChatGenerationParamsProviderTypedDict(TypedDict):
|
||||
allow_fallbacks: NotRequired[Nullable[bool]]
|
||||
r"""Whether to allow backup providers to serve requests
|
||||
@@ -109,10 +227,14 @@ class ChatGenerationParamsProviderTypedDict(TypedDict):
|
||||
r"""The sorting strategy to use for this request, if \"order\" is not specified. When set, no load balancing is performed."""
|
||||
max_price: NotRequired[ChatGenerationParamsMaxPriceTypedDict]
|
||||
r"""The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
|
||||
preferred_min_throughput: NotRequired[Nullable[float]]
|
||||
preferred_max_latency: NotRequired[Nullable[float]]
|
||||
min_throughput: NotRequired[Nullable[float]]
|
||||
max_latency: NotRequired[Nullable[float]]
|
||||
preferred_min_throughput: NotRequired[
|
||||
Nullable[ChatGenerationParamsPreferredMinThroughputUnionTypedDict]
|
||||
]
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
preferred_max_latency: NotRequired[
|
||||
Nullable[ChatGenerationParamsPreferredMaxLatencyUnionTypedDict]
|
||||
]
|
||||
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."""
|
||||
|
||||
|
||||
class ChatGenerationParamsProvider(BaseModel):
|
||||
@@ -160,13 +282,15 @@ class ChatGenerationParamsProvider(BaseModel):
|
||||
max_price: Optional[ChatGenerationParamsMaxPrice] = None
|
||||
r"""The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
|
||||
|
||||
preferred_min_throughput: OptionalNullable[float] = UNSET
|
||||
preferred_min_throughput: OptionalNullable[
|
||||
ChatGenerationParamsPreferredMinThroughputUnion
|
||||
] = UNSET
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
|
||||
preferred_max_latency: OptionalNullable[float] = UNSET
|
||||
|
||||
min_throughput: OptionalNullable[float] = UNSET
|
||||
|
||||
max_latency: OptionalNullable[float] = UNSET
|
||||
preferred_max_latency: OptionalNullable[
|
||||
ChatGenerationParamsPreferredMaxLatencyUnion
|
||||
] = UNSET
|
||||
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."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
@@ -184,8 +308,6 @@ class ChatGenerationParamsProvider(BaseModel):
|
||||
"max_price",
|
||||
"preferred_min_throughput",
|
||||
"preferred_max_latency",
|
||||
"min_throughput",
|
||||
"max_latency",
|
||||
]
|
||||
nullable_fields = [
|
||||
"allow_fallbacks",
|
||||
@@ -200,8 +322,6 @@ class ChatGenerationParamsProvider(BaseModel):
|
||||
"sort",
|
||||
"preferred_min_throughput",
|
||||
"preferred_max_latency",
|
||||
"min_throughput",
|
||||
"max_latency",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
@@ -331,11 +451,31 @@ class ChatGenerationParamsPluginModeration(BaseModel):
|
||||
] = "moderation"
|
||||
|
||||
|
||||
class ChatGenerationParamsPluginAutoRouterTypedDict(TypedDict):
|
||||
id: Literal["auto-router"]
|
||||
enabled: NotRequired[bool]
|
||||
allowed_models: NotRequired[List[str]]
|
||||
|
||||
|
||||
class ChatGenerationParamsPluginAutoRouter(BaseModel):
|
||||
ID: Annotated[
|
||||
Annotated[
|
||||
Literal["auto-router"], AfterValidator(validate_const("auto-router"))
|
||||
],
|
||||
pydantic.Field(alias="id"),
|
||||
] = "auto-router"
|
||||
|
||||
enabled: Optional[bool] = None
|
||||
|
||||
allowed_models: Optional[List[str]] = None
|
||||
|
||||
|
||||
ChatGenerationParamsPluginUnionTypedDict = TypeAliasType(
|
||||
"ChatGenerationParamsPluginUnionTypedDict",
|
||||
Union[
|
||||
ChatGenerationParamsPluginModerationTypedDict,
|
||||
ChatGenerationParamsPluginResponseHealingTypedDict,
|
||||
ChatGenerationParamsPluginAutoRouterTypedDict,
|
||||
ChatGenerationParamsPluginFileParserTypedDict,
|
||||
ChatGenerationParamsPluginWebTypedDict,
|
||||
],
|
||||
@@ -344,6 +484,7 @@ ChatGenerationParamsPluginUnionTypedDict = TypeAliasType(
|
||||
|
||||
ChatGenerationParamsPluginUnion = Annotated[
|
||||
Union[
|
||||
Annotated[ChatGenerationParamsPluginAutoRouter, Tag("auto-router")],
|
||||
Annotated[ChatGenerationParamsPluginModeration, Tag("moderation")],
|
||||
Annotated[ChatGenerationParamsPluginWeb, Tag("web")],
|
||||
Annotated[ChatGenerationParamsPluginFileParser, Tag("file-parser")],
|
||||
@@ -498,6 +639,25 @@ class Debug(BaseModel):
|
||||
echo_upstream_body: Optional[bool] = None
|
||||
|
||||
|
||||
ChatGenerationParamsImageConfigTypedDict = TypeAliasType(
|
||||
"ChatGenerationParamsImageConfigTypedDict", Union[str, float]
|
||||
)
|
||||
|
||||
|
||||
ChatGenerationParamsImageConfig = TypeAliasType(
|
||||
"ChatGenerationParamsImageConfig", Union[str, float]
|
||||
)
|
||||
|
||||
|
||||
Modality = Union[
|
||||
Literal[
|
||||
"text",
|
||||
"image",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
|
||||
|
||||
class ChatGenerationParamsTypedDict(TypedDict):
|
||||
messages: List[MessageTypedDict]
|
||||
provider: NotRequired[Nullable[ChatGenerationParamsProviderTypedDict]]
|
||||
@@ -529,6 +689,8 @@ class ChatGenerationParamsTypedDict(TypedDict):
|
||||
tools: NotRequired[List[ToolDefinitionJSONTypedDict]]
|
||||
top_p: NotRequired[Nullable[float]]
|
||||
debug: NotRequired[DebugTypedDict]
|
||||
image_config: NotRequired[Dict[str, ChatGenerationParamsImageConfigTypedDict]]
|
||||
modalities: NotRequired[List[Modality]]
|
||||
|
||||
|
||||
class ChatGenerationParams(BaseModel):
|
||||
@@ -591,6 +753,12 @@ class ChatGenerationParams(BaseModel):
|
||||
|
||||
debug: Optional[Debug] = None
|
||||
|
||||
image_config: Optional[Dict[str, ChatGenerationParamsImageConfig]] = None
|
||||
|
||||
modalities: Optional[
|
||||
List[Annotated[Modality, PlainValidator(validate_open_enum(False))]]
|
||||
] = None
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
@@ -620,6 +788,8 @@ class ChatGenerationParams(BaseModel):
|
||||
"tools",
|
||||
"top_p",
|
||||
"debug",
|
||||
"image_config",
|
||||
"modalities",
|
||||
]
|
||||
nullable_fields = [
|
||||
"provider",
|
||||
|
||||
@@ -72,6 +72,7 @@ class CompletionTokensDetails(BaseModel):
|
||||
|
||||
class PromptTokensDetailsTypedDict(TypedDict):
|
||||
cached_tokens: NotRequired[float]
|
||||
cache_write_tokens: NotRequired[float]
|
||||
audio_tokens: NotRequired[float]
|
||||
video_tokens: NotRequired[float]
|
||||
|
||||
@@ -79,6 +80,8 @@ class PromptTokensDetailsTypedDict(TypedDict):
|
||||
class PromptTokensDetails(BaseModel):
|
||||
cached_tokens: Optional[float] = None
|
||||
|
||||
cache_write_tokens: Optional[float] = None
|
||||
|
||||
audio_tokens: Optional[float] = None
|
||||
|
||||
video_tokens: Optional[float] = None
|
||||
|
||||
@@ -8,13 +8,13 @@ from typing import List
|
||||
from typing_extensions import Annotated, TypedDict
|
||||
|
||||
|
||||
class TopLogprobTypedDict(TypedDict):
|
||||
class ChatMessageTokenLogprobTopLogprobTypedDict(TypedDict):
|
||||
token: str
|
||||
logprob: float
|
||||
bytes_: Nullable[List[float]]
|
||||
|
||||
|
||||
class TopLogprob(BaseModel):
|
||||
class ChatMessageTokenLogprobTopLogprob(BaseModel):
|
||||
token: str
|
||||
|
||||
logprob: float
|
||||
@@ -56,7 +56,7 @@ class ChatMessageTokenLogprobTypedDict(TypedDict):
|
||||
token: str
|
||||
logprob: float
|
||||
bytes_: Nullable[List[float]]
|
||||
top_logprobs: List[TopLogprobTypedDict]
|
||||
top_logprobs: List[ChatMessageTokenLogprobTopLogprobTypedDict]
|
||||
|
||||
|
||||
class ChatMessageTokenLogprob(BaseModel):
|
||||
@@ -66,7 +66,7 @@ class ChatMessageTokenLogprob(BaseModel):
|
||||
|
||||
bytes_: Annotated[Nullable[List[float]], pydantic.Field(alias="bytes")]
|
||||
|
||||
top_logprobs: List[TopLogprob]
|
||||
top_logprobs: List[ChatMessageTokenLogprobTopLogprob]
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
|
||||
@@ -3,16 +3,24 @@
|
||||
from __future__ import annotations
|
||||
from .responseinputaudio import ResponseInputAudio, ResponseInputAudioTypedDict
|
||||
from .responseinputfile import ResponseInputFile, ResponseInputFileTypedDict
|
||||
from .responseinputimage import ResponseInputImage, ResponseInputImageTypedDict
|
||||
from .responseinputtext import ResponseInputText, ResponseInputTextTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from openrouter.utils import get_discriminator
|
||||
from pydantic import Discriminator, Tag
|
||||
from .responseinputvideo import ResponseInputVideo, ResponseInputVideoTypedDict
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
UnrecognizedStr,
|
||||
)
|
||||
from openrouter.utils import get_discriminator, validate_open_enum
|
||||
from pydantic import Discriminator, Tag, model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypeAliasType, TypedDict
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageType = Literal["message",]
|
||||
OpenResponsesEasyInputMessageTypeMessage = Literal["message",]
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageRoleDeveloper = Literal["developer",]
|
||||
@@ -49,49 +57,114 @@ OpenResponsesEasyInputMessageRoleUnion = TypeAliasType(
|
||||
)
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageContent1TypedDict = TypeAliasType(
|
||||
"OpenResponsesEasyInputMessageContent1TypedDict",
|
||||
OpenResponsesEasyInputMessageContentType = Literal["input_image",]
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageDetail = Union[
|
||||
Literal[
|
||||
"auto",
|
||||
"high",
|
||||
"low",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
|
||||
|
||||
class OpenResponsesEasyInputMessageContentInputImageTypedDict(TypedDict):
|
||||
r"""Image input content item"""
|
||||
|
||||
type: OpenResponsesEasyInputMessageContentType
|
||||
detail: OpenResponsesEasyInputMessageDetail
|
||||
image_url: NotRequired[Nullable[str]]
|
||||
|
||||
|
||||
class OpenResponsesEasyInputMessageContentInputImage(BaseModel):
|
||||
r"""Image input content item"""
|
||||
|
||||
type: OpenResponsesEasyInputMessageContentType
|
||||
|
||||
detail: Annotated[
|
||||
OpenResponsesEasyInputMessageDetail, PlainValidator(validate_open_enum(False))
|
||||
]
|
||||
|
||||
image_url: OptionalNullable[str] = UNSET
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["image_url"]
|
||||
nullable_fields = ["image_url"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageContentUnion1TypedDict = TypeAliasType(
|
||||
"OpenResponsesEasyInputMessageContentUnion1TypedDict",
|
||||
Union[
|
||||
ResponseInputTextTypedDict,
|
||||
ResponseInputAudioTypedDict,
|
||||
ResponseInputImageTypedDict,
|
||||
ResponseInputVideoTypedDict,
|
||||
OpenResponsesEasyInputMessageContentInputImageTypedDict,
|
||||
ResponseInputFileTypedDict,
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageContent1 = Annotated[
|
||||
OpenResponsesEasyInputMessageContentUnion1 = Annotated[
|
||||
Union[
|
||||
Annotated[ResponseInputText, Tag("input_text")],
|
||||
Annotated[ResponseInputImage, Tag("input_image")],
|
||||
Annotated[OpenResponsesEasyInputMessageContentInputImage, Tag("input_image")],
|
||||
Annotated[ResponseInputFile, Tag("input_file")],
|
||||
Annotated[ResponseInputAudio, Tag("input_audio")],
|
||||
Annotated[ResponseInputVideo, Tag("input_video")],
|
||||
],
|
||||
Discriminator(lambda m: get_discriminator(m, "type", "type")),
|
||||
]
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageContent2TypedDict = TypeAliasType(
|
||||
"OpenResponsesEasyInputMessageContent2TypedDict",
|
||||
Union[List[OpenResponsesEasyInputMessageContent1TypedDict], str],
|
||||
OpenResponsesEasyInputMessageContentUnion2TypedDict = TypeAliasType(
|
||||
"OpenResponsesEasyInputMessageContentUnion2TypedDict",
|
||||
Union[List[OpenResponsesEasyInputMessageContentUnion1TypedDict], str],
|
||||
)
|
||||
|
||||
|
||||
OpenResponsesEasyInputMessageContent2 = TypeAliasType(
|
||||
"OpenResponsesEasyInputMessageContent2",
|
||||
Union[List[OpenResponsesEasyInputMessageContent1], str],
|
||||
OpenResponsesEasyInputMessageContentUnion2 = TypeAliasType(
|
||||
"OpenResponsesEasyInputMessageContentUnion2",
|
||||
Union[List[OpenResponsesEasyInputMessageContentUnion1], str],
|
||||
)
|
||||
|
||||
|
||||
class OpenResponsesEasyInputMessageTypedDict(TypedDict):
|
||||
role: OpenResponsesEasyInputMessageRoleUnionTypedDict
|
||||
content: OpenResponsesEasyInputMessageContent2TypedDict
|
||||
type: NotRequired[OpenResponsesEasyInputMessageType]
|
||||
content: OpenResponsesEasyInputMessageContentUnion2TypedDict
|
||||
type: NotRequired[OpenResponsesEasyInputMessageTypeMessage]
|
||||
|
||||
|
||||
class OpenResponsesEasyInputMessage(BaseModel):
|
||||
role: OpenResponsesEasyInputMessageRoleUnion
|
||||
|
||||
content: OpenResponsesEasyInputMessageContent2
|
||||
content: OpenResponsesEasyInputMessageContentUnion2
|
||||
|
||||
type: Optional[OpenResponsesEasyInputMessageType] = None
|
||||
type: Optional[OpenResponsesEasyInputMessageTypeMessage] = None
|
||||
|
||||
@@ -60,9 +60,9 @@ OpenResponsesInput1TypedDict = TypeAliasType(
|
||||
OpenResponsesFunctionCallOutputTypedDict,
|
||||
ResponsesOutputMessageTypedDict,
|
||||
OpenResponsesFunctionToolCallTypedDict,
|
||||
ResponsesOutputItemReasoningTypedDict,
|
||||
ResponsesOutputItemFunctionCallTypedDict,
|
||||
OpenResponsesReasoningTypedDict,
|
||||
ResponsesOutputItemReasoningTypedDict,
|
||||
],
|
||||
)
|
||||
|
||||
@@ -78,9 +78,9 @@ OpenResponsesInput1 = TypeAliasType(
|
||||
OpenResponsesFunctionCallOutput,
|
||||
ResponsesOutputMessage,
|
||||
OpenResponsesFunctionToolCall,
|
||||
ResponsesOutputItemReasoning,
|
||||
ResponsesOutputItemFunctionCall,
|
||||
OpenResponsesReasoning,
|
||||
ResponsesOutputItemReasoning,
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
@@ -3,16 +3,24 @@
|
||||
from __future__ import annotations
|
||||
from .responseinputaudio import ResponseInputAudio, ResponseInputAudioTypedDict
|
||||
from .responseinputfile import ResponseInputFile, ResponseInputFileTypedDict
|
||||
from .responseinputimage import ResponseInputImage, ResponseInputImageTypedDict
|
||||
from .responseinputtext import ResponseInputText, ResponseInputTextTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from openrouter.utils import get_discriminator
|
||||
from pydantic import Discriminator, Tag
|
||||
from .responseinputvideo import ResponseInputVideo, ResponseInputVideoTypedDict
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
UnrecognizedStr,
|
||||
)
|
||||
from openrouter.utils import get_discriminator, validate_open_enum
|
||||
from pydantic import Discriminator, Tag, model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypeAliasType, TypedDict
|
||||
|
||||
|
||||
OpenResponsesInputMessageItemType = Literal["message",]
|
||||
OpenResponsesInputMessageItemTypeMessage = Literal["message",]
|
||||
|
||||
|
||||
OpenResponsesInputMessageItemRoleDeveloper = Literal["developer",]
|
||||
@@ -44,23 +52,88 @@ OpenResponsesInputMessageItemRoleUnion = TypeAliasType(
|
||||
)
|
||||
|
||||
|
||||
OpenResponsesInputMessageItemContentTypedDict = TypeAliasType(
|
||||
"OpenResponsesInputMessageItemContentTypedDict",
|
||||
OpenResponsesInputMessageItemContentType = Literal["input_image",]
|
||||
|
||||
|
||||
OpenResponsesInputMessageItemDetail = Union[
|
||||
Literal[
|
||||
"auto",
|
||||
"high",
|
||||
"low",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
|
||||
|
||||
class OpenResponsesInputMessageItemContentInputImageTypedDict(TypedDict):
|
||||
r"""Image input content item"""
|
||||
|
||||
type: OpenResponsesInputMessageItemContentType
|
||||
detail: OpenResponsesInputMessageItemDetail
|
||||
image_url: NotRequired[Nullable[str]]
|
||||
|
||||
|
||||
class OpenResponsesInputMessageItemContentInputImage(BaseModel):
|
||||
r"""Image input content item"""
|
||||
|
||||
type: OpenResponsesInputMessageItemContentType
|
||||
|
||||
detail: Annotated[
|
||||
OpenResponsesInputMessageItemDetail, PlainValidator(validate_open_enum(False))
|
||||
]
|
||||
|
||||
image_url: OptionalNullable[str] = UNSET
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["image_url"]
|
||||
nullable_fields = ["image_url"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
OpenResponsesInputMessageItemContentUnionTypedDict = TypeAliasType(
|
||||
"OpenResponsesInputMessageItemContentUnionTypedDict",
|
||||
Union[
|
||||
ResponseInputTextTypedDict,
|
||||
ResponseInputAudioTypedDict,
|
||||
ResponseInputImageTypedDict,
|
||||
ResponseInputVideoTypedDict,
|
||||
OpenResponsesInputMessageItemContentInputImageTypedDict,
|
||||
ResponseInputFileTypedDict,
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
OpenResponsesInputMessageItemContent = Annotated[
|
||||
OpenResponsesInputMessageItemContentUnion = Annotated[
|
||||
Union[
|
||||
Annotated[ResponseInputText, Tag("input_text")],
|
||||
Annotated[ResponseInputImage, Tag("input_image")],
|
||||
Annotated[OpenResponsesInputMessageItemContentInputImage, Tag("input_image")],
|
||||
Annotated[ResponseInputFile, Tag("input_file")],
|
||||
Annotated[ResponseInputAudio, Tag("input_audio")],
|
||||
Annotated[ResponseInputVideo, Tag("input_video")],
|
||||
],
|
||||
Discriminator(lambda m: get_discriminator(m, "type", "type")),
|
||||
]
|
||||
@@ -68,16 +141,16 @@ OpenResponsesInputMessageItemContent = Annotated[
|
||||
|
||||
class OpenResponsesInputMessageItemTypedDict(TypedDict):
|
||||
role: OpenResponsesInputMessageItemRoleUnionTypedDict
|
||||
content: List[OpenResponsesInputMessageItemContentTypedDict]
|
||||
content: List[OpenResponsesInputMessageItemContentUnionTypedDict]
|
||||
id: NotRequired[str]
|
||||
type: NotRequired[OpenResponsesInputMessageItemType]
|
||||
type: NotRequired[OpenResponsesInputMessageItemTypeMessage]
|
||||
|
||||
|
||||
class OpenResponsesInputMessageItem(BaseModel):
|
||||
role: OpenResponsesInputMessageItemRoleUnion
|
||||
|
||||
content: List[OpenResponsesInputMessageItemContent]
|
||||
content: List[OpenResponsesInputMessageItemContentUnion]
|
||||
|
||||
id: Optional[str] = None
|
||||
|
||||
type: Optional[OpenResponsesInputMessageItemType] = None
|
||||
type: Optional[OpenResponsesInputMessageItemTypeMessage] = None
|
||||
|
||||
@@ -149,24 +149,27 @@ class OpenResponsesNonStreamingResponseTypedDict(TypedDict):
|
||||
object: Object
|
||||
created_at: float
|
||||
model: str
|
||||
status: OpenAIResponsesResponseStatus
|
||||
completed_at: Nullable[float]
|
||||
output: List[ResponsesOutputItemTypedDict]
|
||||
error: Nullable[ResponsesErrorFieldTypedDict]
|
||||
r"""Error information returned from the API"""
|
||||
incomplete_details: Nullable[OpenAIResponsesIncompleteDetailsTypedDict]
|
||||
temperature: Nullable[float]
|
||||
top_p: Nullable[float]
|
||||
presence_penalty: Nullable[float]
|
||||
frequency_penalty: Nullable[float]
|
||||
instructions: Nullable[OpenAIResponsesInputUnionTypedDict]
|
||||
metadata: Nullable[Dict[str, str]]
|
||||
r"""Metadata key-value pairs for the request. Keys must be ≤64 characters and cannot contain brackets. Values must be ≤512 characters. Maximum 16 pairs allowed."""
|
||||
tools: List[OpenResponsesNonStreamingResponseToolUnionTypedDict]
|
||||
tool_choice: OpenAIResponsesToolChoiceUnionTypedDict
|
||||
parallel_tool_calls: bool
|
||||
status: NotRequired[OpenAIResponsesResponseStatus]
|
||||
user: NotRequired[Nullable[str]]
|
||||
output_text: NotRequired[str]
|
||||
prompt_cache_key: NotRequired[Nullable[str]]
|
||||
safety_identifier: NotRequired[Nullable[str]]
|
||||
usage: NotRequired[OpenResponsesUsageTypedDict]
|
||||
usage: NotRequired[Nullable[OpenResponsesUsageTypedDict]]
|
||||
r"""Token usage information for the response"""
|
||||
max_tool_calls: NotRequired[Nullable[float]]
|
||||
top_logprobs: NotRequired[float]
|
||||
@@ -193,6 +196,12 @@ class OpenResponsesNonStreamingResponse(BaseModel):
|
||||
|
||||
model: str
|
||||
|
||||
status: Annotated[
|
||||
OpenAIResponsesResponseStatus, PlainValidator(validate_open_enum(False))
|
||||
]
|
||||
|
||||
completed_at: Nullable[float]
|
||||
|
||||
output: List[ResponsesOutputItem]
|
||||
|
||||
error: Nullable[ResponsesErrorField]
|
||||
@@ -204,6 +213,10 @@ class OpenResponsesNonStreamingResponse(BaseModel):
|
||||
|
||||
top_p: Nullable[float]
|
||||
|
||||
presence_penalty: Nullable[float]
|
||||
|
||||
frequency_penalty: Nullable[float]
|
||||
|
||||
instructions: Nullable[OpenAIResponsesInputUnion]
|
||||
|
||||
metadata: Nullable[Dict[str, str]]
|
||||
@@ -215,11 +228,6 @@ class OpenResponsesNonStreamingResponse(BaseModel):
|
||||
|
||||
parallel_tool_calls: bool
|
||||
|
||||
status: Annotated[
|
||||
Optional[OpenAIResponsesResponseStatus],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
|
||||
user: OptionalNullable[str] = UNSET
|
||||
|
||||
output_text: Optional[str] = None
|
||||
@@ -228,7 +236,7 @@ class OpenResponsesNonStreamingResponse(BaseModel):
|
||||
|
||||
safety_identifier: OptionalNullable[str] = UNSET
|
||||
|
||||
usage: Optional[OpenResponsesUsage] = None
|
||||
usage: OptionalNullable[OpenResponsesUsage] = UNSET
|
||||
r"""Token usage information for the response"""
|
||||
|
||||
max_tool_calls: OptionalNullable[float] = UNSET
|
||||
@@ -263,7 +271,6 @@ class OpenResponsesNonStreamingResponse(BaseModel):
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"status",
|
||||
"user",
|
||||
"output_text",
|
||||
"prompt_cache_key",
|
||||
@@ -282,15 +289,19 @@ class OpenResponsesNonStreamingResponse(BaseModel):
|
||||
"text",
|
||||
]
|
||||
nullable_fields = [
|
||||
"completed_at",
|
||||
"user",
|
||||
"prompt_cache_key",
|
||||
"safety_identifier",
|
||||
"error",
|
||||
"incomplete_details",
|
||||
"usage",
|
||||
"max_tool_calls",
|
||||
"max_output_tokens",
|
||||
"temperature",
|
||||
"top_p",
|
||||
"presence_penalty",
|
||||
"frequency_penalty",
|
||||
"instructions",
|
||||
"metadata",
|
||||
"prompt",
|
||||
|
||||
@@ -55,6 +55,7 @@ OpenResponsesReasoningFormat = Union[
|
||||
Literal[
|
||||
"unknown",
|
||||
"openai-responses-v1",
|
||||
"azure-openai-responses-v1",
|
||||
"xai-responses-v1",
|
||||
"anthropic-claude-v1",
|
||||
"google-gemini-v1",
|
||||
|
||||
@@ -34,10 +34,16 @@ from .openresponseswebsearchtool import (
|
||||
OpenResponsesWebSearchToolTypedDict,
|
||||
)
|
||||
from .pdfparseroptions import PDFParserOptions, PDFParserOptionsTypedDict
|
||||
from .preferredmaxlatency import PreferredMaxLatency, PreferredMaxLatencyTypedDict
|
||||
from .preferredminthroughput import (
|
||||
PreferredMinThroughput,
|
||||
PreferredMinThroughputTypedDict,
|
||||
)
|
||||
from .providername import ProviderName
|
||||
from .providersort import ProviderSort
|
||||
from .providersortconfig import ProviderSortConfig, ProviderSortConfigTypedDict
|
||||
from .quantization import Quantization
|
||||
from .responsesoutputmodality import ResponsesOutputModality
|
||||
from .websearchengine import WebSearchEngine
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
@@ -139,6 +145,16 @@ OpenResponsesRequestToolUnion = Annotated[
|
||||
]
|
||||
|
||||
|
||||
OpenResponsesRequestImageConfigTypedDict = TypeAliasType(
|
||||
"OpenResponsesRequestImageConfigTypedDict", Union[str, float]
|
||||
)
|
||||
|
||||
|
||||
OpenResponsesRequestImageConfig = TypeAliasType(
|
||||
"OpenResponsesRequestImageConfig", Union[str, float]
|
||||
)
|
||||
|
||||
|
||||
ServiceTier = Literal["auto",]
|
||||
|
||||
|
||||
@@ -269,14 +285,10 @@ class OpenResponsesRequestProviderTypedDict(TypedDict):
|
||||
r"""The sorting strategy to use for this request, if \"order\" is not specified. When set, no load balancing is performed."""
|
||||
max_price: NotRequired[OpenResponsesRequestMaxPriceTypedDict]
|
||||
r"""The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
|
||||
preferred_min_throughput: NotRequired[Nullable[float]]
|
||||
r"""Preferred minimum throughput (in tokens per second). Endpoints below this threshold 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."""
|
||||
preferred_max_latency: NotRequired[Nullable[float]]
|
||||
r"""Preferred maximum latency (in seconds). Endpoints above this threshold 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."""
|
||||
min_throughput: NotRequired[Nullable[float]]
|
||||
r"""**DEPRECATED** Use preferred_min_throughput instead. Backwards-compatible alias for preferred_min_throughput."""
|
||||
max_latency: NotRequired[Nullable[float]]
|
||||
r"""**DEPRECATED** Use preferred_max_latency instead. Backwards-compatible alias for preferred_max_latency."""
|
||||
preferred_min_throughput: NotRequired[Nullable[PreferredMinThroughputTypedDict]]
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
preferred_max_latency: NotRequired[Nullable[PreferredMaxLatencyTypedDict]]
|
||||
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."""
|
||||
|
||||
|
||||
class OpenResponsesRequestProvider(BaseModel):
|
||||
@@ -327,27 +339,11 @@ class OpenResponsesRequestProvider(BaseModel):
|
||||
max_price: Optional[OpenResponsesRequestMaxPrice] = None
|
||||
r"""The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
|
||||
|
||||
preferred_min_throughput: OptionalNullable[float] = UNSET
|
||||
r"""Preferred minimum throughput (in tokens per second). Endpoints below this threshold 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."""
|
||||
preferred_min_throughput: OptionalNullable[PreferredMinThroughput] = UNSET
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
|
||||
preferred_max_latency: OptionalNullable[float] = UNSET
|
||||
r"""Preferred maximum latency (in seconds). Endpoints above this threshold 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."""
|
||||
|
||||
min_throughput: Annotated[
|
||||
OptionalNullable[float],
|
||||
pydantic.Field(
|
||||
deprecated="warning: ** DEPRECATED ** - Use preferred_min_throughput instead.."
|
||||
),
|
||||
] = UNSET
|
||||
r"""**DEPRECATED** Use preferred_min_throughput instead. Backwards-compatible alias for preferred_min_throughput."""
|
||||
|
||||
max_latency: Annotated[
|
||||
OptionalNullable[float],
|
||||
pydantic.Field(
|
||||
deprecated="warning: ** DEPRECATED ** - Use preferred_max_latency instead.."
|
||||
),
|
||||
] = UNSET
|
||||
r"""**DEPRECATED** Use preferred_max_latency instead. Backwards-compatible alias for preferred_max_latency."""
|
||||
preferred_max_latency: OptionalNullable[PreferredMaxLatency] = UNSET
|
||||
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."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
@@ -365,8 +361,6 @@ class OpenResponsesRequestProvider(BaseModel):
|
||||
"max_price",
|
||||
"preferred_min_throughput",
|
||||
"preferred_max_latency",
|
||||
"min_throughput",
|
||||
"max_latency",
|
||||
]
|
||||
nullable_fields = [
|
||||
"allow_fallbacks",
|
||||
@@ -381,8 +375,6 @@ class OpenResponsesRequestProvider(BaseModel):
|
||||
"sort",
|
||||
"preferred_min_throughput",
|
||||
"preferred_max_latency",
|
||||
"min_throughput",
|
||||
"max_latency",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
@@ -488,11 +480,33 @@ class OpenResponsesRequestPluginModeration(BaseModel):
|
||||
id: IDModeration
|
||||
|
||||
|
||||
IDAutoRouter = Literal["auto-router",]
|
||||
|
||||
|
||||
class OpenResponsesRequestPluginAutoRouterTypedDict(TypedDict):
|
||||
id: IDAutoRouter
|
||||
enabled: NotRequired[bool]
|
||||
r"""Set to false to disable the auto-router plugin for this request. Defaults to true."""
|
||||
allowed_models: NotRequired[List[str]]
|
||||
r"""List of model patterns to filter which models the auto-router can route between. Supports wildcards (e.g., \"anthropic/*\" matches all Anthropic models). When not specified, uses the default supported models list."""
|
||||
|
||||
|
||||
class OpenResponsesRequestPluginAutoRouter(BaseModel):
|
||||
id: IDAutoRouter
|
||||
|
||||
enabled: Optional[bool] = None
|
||||
r"""Set to false to disable the auto-router plugin for this request. Defaults to true."""
|
||||
|
||||
allowed_models: Optional[List[str]] = None
|
||||
r"""List of model patterns to filter which models the auto-router can route between. Supports wildcards (e.g., \"anthropic/*\" matches all Anthropic models). When not specified, uses the default supported models list."""
|
||||
|
||||
|
||||
OpenResponsesRequestPluginUnionTypedDict = TypeAliasType(
|
||||
"OpenResponsesRequestPluginUnionTypedDict",
|
||||
Union[
|
||||
OpenResponsesRequestPluginModerationTypedDict,
|
||||
OpenResponsesRequestPluginResponseHealingTypedDict,
|
||||
OpenResponsesRequestPluginAutoRouterTypedDict,
|
||||
OpenResponsesRequestPluginFileParserTypedDict,
|
||||
OpenResponsesRequestPluginWebTypedDict,
|
||||
],
|
||||
@@ -501,6 +515,7 @@ OpenResponsesRequestPluginUnionTypedDict = TypeAliasType(
|
||||
|
||||
OpenResponsesRequestPluginUnion = Annotated[
|
||||
Union[
|
||||
Annotated[OpenResponsesRequestPluginAutoRouter, Tag("auto-router")],
|
||||
Annotated[OpenResponsesRequestPluginModeration, Tag("moderation")],
|
||||
Annotated[OpenResponsesRequestPluginWeb, Tag("web")],
|
||||
Annotated[OpenResponsesRequestPluginFileParser, Tag("file-parser")],
|
||||
@@ -530,7 +545,15 @@ class OpenResponsesRequestTypedDict(TypedDict):
|
||||
max_output_tokens: NotRequired[Nullable[float]]
|
||||
temperature: NotRequired[Nullable[float]]
|
||||
top_p: NotRequired[Nullable[float]]
|
||||
top_logprobs: NotRequired[Nullable[int]]
|
||||
max_tool_calls: NotRequired[Nullable[int]]
|
||||
presence_penalty: NotRequired[Nullable[float]]
|
||||
frequency_penalty: NotRequired[Nullable[float]]
|
||||
top_k: NotRequired[float]
|
||||
image_config: NotRequired[Dict[str, OpenResponsesRequestImageConfigTypedDict]]
|
||||
r"""Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/features/multimodal/image-generation for more details."""
|
||||
modalities: NotRequired[List[ResponsesOutputModality]]
|
||||
r"""Output modalities for the response. Supported values are \"text\" and \"image\"."""
|
||||
prompt_cache_key: NotRequired[Nullable[str]]
|
||||
previous_response_id: NotRequired[Nullable[str]]
|
||||
prompt: NotRequired[Nullable[OpenAIResponsesPromptTypedDict]]
|
||||
@@ -584,8 +607,28 @@ class OpenResponsesRequest(BaseModel):
|
||||
|
||||
top_p: OptionalNullable[float] = UNSET
|
||||
|
||||
top_logprobs: OptionalNullable[int] = UNSET
|
||||
|
||||
max_tool_calls: OptionalNullable[int] = UNSET
|
||||
|
||||
presence_penalty: OptionalNullable[float] = UNSET
|
||||
|
||||
frequency_penalty: OptionalNullable[float] = UNSET
|
||||
|
||||
top_k: Optional[float] = None
|
||||
|
||||
image_config: Optional[Dict[str, OpenResponsesRequestImageConfig]] = None
|
||||
r"""Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/features/multimodal/image-generation for more details."""
|
||||
|
||||
modalities: Optional[
|
||||
List[
|
||||
Annotated[
|
||||
ResponsesOutputModality, PlainValidator(validate_open_enum(False))
|
||||
]
|
||||
]
|
||||
] = None
|
||||
r"""Output modalities for the response. Supported values are \"text\" and \"image\"."""
|
||||
|
||||
prompt_cache_key: OptionalNullable[str] = UNSET
|
||||
|
||||
previous_response_id: OptionalNullable[str] = UNSET
|
||||
@@ -645,7 +688,13 @@ class OpenResponsesRequest(BaseModel):
|
||||
"max_output_tokens",
|
||||
"temperature",
|
||||
"top_p",
|
||||
"top_logprobs",
|
||||
"max_tool_calls",
|
||||
"presence_penalty",
|
||||
"frequency_penalty",
|
||||
"top_k",
|
||||
"image_config",
|
||||
"modalities",
|
||||
"prompt_cache_key",
|
||||
"previous_response_id",
|
||||
"prompt",
|
||||
@@ -669,6 +718,10 @@ class OpenResponsesRequest(BaseModel):
|
||||
"max_output_tokens",
|
||||
"temperature",
|
||||
"top_p",
|
||||
"top_logprobs",
|
||||
"max_tool_calls",
|
||||
"presence_penalty",
|
||||
"frequency_penalty",
|
||||
"prompt_cache_key",
|
||||
"previous_response_id",
|
||||
"prompt",
|
||||
|
||||
@@ -0,0 +1,71 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class PercentileLatencyCutoffsTypedDict(TypedDict):
|
||||
r"""Percentile-based latency cutoffs. All specified cutoffs must be met for an endpoint to be preferred."""
|
||||
|
||||
p50: NotRequired[Nullable[float]]
|
||||
r"""Maximum p50 latency (seconds)"""
|
||||
p75: NotRequired[Nullable[float]]
|
||||
r"""Maximum p75 latency (seconds)"""
|
||||
p90: NotRequired[Nullable[float]]
|
||||
r"""Maximum p90 latency (seconds)"""
|
||||
p99: NotRequired[Nullable[float]]
|
||||
r"""Maximum p99 latency (seconds)"""
|
||||
|
||||
|
||||
class PercentileLatencyCutoffs(BaseModel):
|
||||
r"""Percentile-based latency cutoffs. All specified cutoffs must be met for an endpoint to be preferred."""
|
||||
|
||||
p50: OptionalNullable[float] = UNSET
|
||||
r"""Maximum p50 latency (seconds)"""
|
||||
|
||||
p75: OptionalNullable[float] = UNSET
|
||||
r"""Maximum p75 latency (seconds)"""
|
||||
|
||||
p90: OptionalNullable[float] = UNSET
|
||||
r"""Maximum p90 latency (seconds)"""
|
||||
|
||||
p99: OptionalNullable[float] = UNSET
|
||||
r"""Maximum p99 latency (seconds)"""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["p50", "p75", "p90", "p99"]
|
||||
nullable_fields = ["p50", "p75", "p90", "p99"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,34 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class PercentileStatsTypedDict(TypedDict):
|
||||
r"""Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests."""
|
||||
|
||||
p50: float
|
||||
r"""Median (50th percentile)"""
|
||||
p75: float
|
||||
r"""75th percentile"""
|
||||
p90: float
|
||||
r"""90th percentile"""
|
||||
p99: float
|
||||
r"""99th percentile"""
|
||||
|
||||
|
||||
class PercentileStats(BaseModel):
|
||||
r"""Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests."""
|
||||
|
||||
p50: float
|
||||
r"""Median (50th percentile)"""
|
||||
|
||||
p75: float
|
||||
r"""75th percentile"""
|
||||
|
||||
p90: float
|
||||
r"""90th percentile"""
|
||||
|
||||
p99: float
|
||||
r"""99th percentile"""
|
||||
@@ -0,0 +1,71 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class PercentileThroughputCutoffsTypedDict(TypedDict):
|
||||
r"""Percentile-based throughput cutoffs. All specified cutoffs must be met for an endpoint to be preferred."""
|
||||
|
||||
p50: NotRequired[Nullable[float]]
|
||||
r"""Minimum p50 throughput (tokens/sec)"""
|
||||
p75: NotRequired[Nullable[float]]
|
||||
r"""Minimum p75 throughput (tokens/sec)"""
|
||||
p90: NotRequired[Nullable[float]]
|
||||
r"""Minimum p90 throughput (tokens/sec)"""
|
||||
p99: NotRequired[Nullable[float]]
|
||||
r"""Minimum p99 throughput (tokens/sec)"""
|
||||
|
||||
|
||||
class PercentileThroughputCutoffs(BaseModel):
|
||||
r"""Percentile-based throughput cutoffs. All specified cutoffs must be met for an endpoint to be preferred."""
|
||||
|
||||
p50: OptionalNullable[float] = UNSET
|
||||
r"""Minimum p50 throughput (tokens/sec)"""
|
||||
|
||||
p75: OptionalNullable[float] = UNSET
|
||||
r"""Minimum p75 throughput (tokens/sec)"""
|
||||
|
||||
p90: OptionalNullable[float] = UNSET
|
||||
r"""Minimum p90 throughput (tokens/sec)"""
|
||||
|
||||
p99: OptionalNullable[float] = UNSET
|
||||
r"""Minimum p99 throughput (tokens/sec)"""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["p50", "p75", "p90", "p99"]
|
||||
nullable_fields = ["p50", "p75", "p90", "p99"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,21 @@
|
||||
"""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."""
|
||||
@@ -0,0 +1,22 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .percentilethroughputcutoffs import (
|
||||
PercentileThroughputCutoffs,
|
||||
PercentileThroughputCutoffsTypedDict,
|
||||
)
|
||||
from typing import Any, Union
|
||||
from typing_extensions import TypeAliasType
|
||||
|
||||
|
||||
PreferredMinThroughputTypedDict = TypeAliasType(
|
||||
"PreferredMinThroughputTypedDict",
|
||||
Union[PercentileThroughputCutoffsTypedDict, float, Any],
|
||||
)
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
|
||||
|
||||
PreferredMinThroughput = TypeAliasType(
|
||||
"PreferredMinThroughput", Union[PercentileThroughputCutoffs, float, Any]
|
||||
)
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
@@ -33,12 +33,12 @@ ProviderName = Union[
|
||||
"Fireworks",
|
||||
"Friendli",
|
||||
"GMICloud",
|
||||
"GoPomelo",
|
||||
"Google",
|
||||
"Google AI Studio",
|
||||
"Groq",
|
||||
"Hyperbolic",
|
||||
"Inception",
|
||||
"Inceptron",
|
||||
"InferenceNet",
|
||||
"Infermatic",
|
||||
"Inflection",
|
||||
@@ -63,13 +63,14 @@ ProviderName = Union[
|
||||
"Phala",
|
||||
"Relace",
|
||||
"SambaNova",
|
||||
"Seed",
|
||||
"SiliconFlow",
|
||||
"Sourceful",
|
||||
"Stealth",
|
||||
"StreamLake",
|
||||
"Switchpoint",
|
||||
"Targon",
|
||||
"Together",
|
||||
"Upstage",
|
||||
"Venice",
|
||||
"WandB",
|
||||
"Xiaomi",
|
||||
|
||||
@@ -2,6 +2,11 @@
|
||||
|
||||
from __future__ import annotations
|
||||
from .datacollection import DataCollection
|
||||
from .preferredmaxlatency import PreferredMaxLatency, PreferredMaxLatencyTypedDict
|
||||
from .preferredminthroughput import (
|
||||
PreferredMinThroughput,
|
||||
PreferredMinThroughputTypedDict,
|
||||
)
|
||||
from .providername import ProviderName
|
||||
from .providersort import ProviderSort
|
||||
from .quantization import Quantization
|
||||
@@ -14,7 +19,6 @@ from openrouter.types import (
|
||||
UnrecognizedStr,
|
||||
)
|
||||
from openrouter.utils import validate_open_enum
|
||||
import pydantic
|
||||
from pydantic import model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Literal, Optional, Union
|
||||
@@ -234,14 +238,10 @@ class ProviderPreferencesTypedDict(TypedDict):
|
||||
sort: NotRequired[Nullable[ProviderPreferencesSortUnionTypedDict]]
|
||||
max_price: NotRequired[ProviderPreferencesMaxPriceTypedDict]
|
||||
r"""The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
|
||||
preferred_min_throughput: NotRequired[Nullable[float]]
|
||||
r"""Preferred minimum throughput (in tokens per second). Endpoints below this threshold 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."""
|
||||
preferred_max_latency: NotRequired[Nullable[float]]
|
||||
r"""Preferred maximum latency (in seconds). Endpoints above this threshold 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."""
|
||||
min_throughput: NotRequired[Nullable[float]]
|
||||
r"""**DEPRECATED** Use preferred_min_throughput instead. Backwards-compatible alias for preferred_min_throughput."""
|
||||
max_latency: NotRequired[Nullable[float]]
|
||||
r"""**DEPRECATED** Use preferred_max_latency instead. Backwards-compatible alias for preferred_max_latency."""
|
||||
preferred_min_throughput: NotRequired[Nullable[PreferredMinThroughputTypedDict]]
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
preferred_max_latency: NotRequired[Nullable[PreferredMaxLatencyTypedDict]]
|
||||
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."""
|
||||
|
||||
|
||||
class ProviderPreferences(BaseModel):
|
||||
@@ -291,27 +291,11 @@ class ProviderPreferences(BaseModel):
|
||||
max_price: Optional[ProviderPreferencesMaxPrice] = None
|
||||
r"""The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
|
||||
|
||||
preferred_min_throughput: OptionalNullable[float] = UNSET
|
||||
r"""Preferred minimum throughput (in tokens per second). Endpoints below this threshold 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."""
|
||||
preferred_min_throughput: OptionalNullable[PreferredMinThroughput] = UNSET
|
||||
r"""Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below 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."""
|
||||
|
||||
preferred_max_latency: OptionalNullable[float] = UNSET
|
||||
r"""Preferred maximum latency (in seconds). Endpoints above this threshold 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."""
|
||||
|
||||
min_throughput: Annotated[
|
||||
OptionalNullable[float],
|
||||
pydantic.Field(
|
||||
deprecated="warning: ** DEPRECATED ** - Use preferred_min_throughput instead.."
|
||||
),
|
||||
] = UNSET
|
||||
r"""**DEPRECATED** Use preferred_min_throughput instead. Backwards-compatible alias for preferred_min_throughput."""
|
||||
|
||||
max_latency: Annotated[
|
||||
OptionalNullable[float],
|
||||
pydantic.Field(
|
||||
deprecated="warning: ** DEPRECATED ** - Use preferred_max_latency instead.."
|
||||
),
|
||||
] = UNSET
|
||||
r"""**DEPRECATED** Use preferred_max_latency instead. Backwards-compatible alias for preferred_max_latency."""
|
||||
preferred_max_latency: OptionalNullable[PreferredMaxLatency] = UNSET
|
||||
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."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
@@ -329,8 +313,6 @@ class ProviderPreferences(BaseModel):
|
||||
"max_price",
|
||||
"preferred_min_throughput",
|
||||
"preferred_max_latency",
|
||||
"min_throughput",
|
||||
"max_latency",
|
||||
]
|
||||
nullable_fields = [
|
||||
"allow_fallbacks",
|
||||
@@ -345,8 +327,6 @@ class ProviderPreferences(BaseModel):
|
||||
"sort",
|
||||
"preferred_min_throughput",
|
||||
"preferred_max_latency",
|
||||
"min_throughput",
|
||||
"max_latency",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
from .endpointstatus import EndpointStatus
|
||||
from .parameter import Parameter
|
||||
from .percentilestats import PercentileStats, PercentileStatsTypedDict
|
||||
from .providername import ProviderName
|
||||
from openrouter.types import BaseModel, Nullable, UNSET_SENTINEL, UnrecognizedStr
|
||||
from openrouter.utils import validate_open_enum
|
||||
@@ -111,6 +112,9 @@ class PublicEndpointTypedDict(TypedDict):
|
||||
supported_parameters: List[Parameter]
|
||||
uptime_last_30m: Nullable[float]
|
||||
supports_implicit_caching: bool
|
||||
latency_last_30m: Nullable[PercentileStatsTypedDict]
|
||||
r"""Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests."""
|
||||
throughput_last_30m: Nullable[PercentileStatsTypedDict]
|
||||
status: NotRequired[EndpointStatus]
|
||||
|
||||
|
||||
@@ -145,6 +149,11 @@ class PublicEndpoint(BaseModel):
|
||||
|
||||
supports_implicit_caching: bool
|
||||
|
||||
latency_last_30m: Nullable[PercentileStats]
|
||||
r"""Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests."""
|
||||
|
||||
throughput_last_30m: Nullable[PercentileStats]
|
||||
|
||||
status: Annotated[
|
||||
Optional[EndpointStatus], PlainValidator(validate_open_enum(True))
|
||||
] = None
|
||||
@@ -157,6 +166,8 @@ class PublicEndpoint(BaseModel):
|
||||
"max_completion_tokens",
|
||||
"max_prompt_tokens",
|
||||
"uptime_last_30m",
|
||||
"latency_last_30m",
|
||||
"throughput_last_30m",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
ResponseInputVideoType = Literal["input_video",]
|
||||
|
||||
|
||||
class ResponseInputVideoTypedDict(TypedDict):
|
||||
r"""Video input content item"""
|
||||
|
||||
type: ResponseInputVideoType
|
||||
video_url: str
|
||||
r"""A base64 data URL or remote URL that resolves to a video file"""
|
||||
|
||||
|
||||
class ResponseInputVideo(BaseModel):
|
||||
r"""Video input content item"""
|
||||
|
||||
type: ResponseInputVideoType
|
||||
|
||||
video_url: str
|
||||
r"""A base64 data URL or remote URL that resolves to a video file"""
|
||||
@@ -6,17 +6,50 @@ from .openairesponsesannotation import (
|
||||
OpenAIResponsesAnnotationTypedDict,
|
||||
)
|
||||
from openrouter.types import BaseModel
|
||||
import pydantic
|
||||
from typing import List, Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
ResponseOutputTextType = Literal["output_text",]
|
||||
|
||||
|
||||
class ResponseOutputTextTopLogprobTypedDict(TypedDict):
|
||||
token: str
|
||||
bytes_: List[float]
|
||||
logprob: float
|
||||
|
||||
|
||||
class ResponseOutputTextTopLogprob(BaseModel):
|
||||
token: str
|
||||
|
||||
bytes_: Annotated[List[float], pydantic.Field(alias="bytes")]
|
||||
|
||||
logprob: float
|
||||
|
||||
|
||||
class LogprobTypedDict(TypedDict):
|
||||
token: str
|
||||
bytes_: List[float]
|
||||
logprob: float
|
||||
top_logprobs: List[ResponseOutputTextTopLogprobTypedDict]
|
||||
|
||||
|
||||
class Logprob(BaseModel):
|
||||
token: str
|
||||
|
||||
bytes_: Annotated[List[float], pydantic.Field(alias="bytes")]
|
||||
|
||||
logprob: float
|
||||
|
||||
top_logprobs: List[ResponseOutputTextTopLogprob]
|
||||
|
||||
|
||||
class ResponseOutputTextTypedDict(TypedDict):
|
||||
type: ResponseOutputTextType
|
||||
text: str
|
||||
annotations: NotRequired[List[OpenAIResponsesAnnotationTypedDict]]
|
||||
logprobs: NotRequired[List[LogprobTypedDict]]
|
||||
|
||||
|
||||
class ResponseOutputText(BaseModel):
|
||||
@@ -25,3 +58,5 @@ class ResponseOutputText(BaseModel):
|
||||
text: str
|
||||
|
||||
annotations: Optional[List[OpenAIResponsesAnnotation]] = None
|
||||
|
||||
logprobs: Optional[List[Logprob]] = None
|
||||
|
||||
@@ -38,8 +38,8 @@ ResponsesOutputItemTypedDict = TypeAliasType(
|
||||
ResponsesOutputItemFileSearchCallTypedDict,
|
||||
ResponsesImageGenerationCallTypedDict,
|
||||
ResponsesOutputMessageTypedDict,
|
||||
ResponsesOutputItemReasoningTypedDict,
|
||||
ResponsesOutputItemFunctionCallTypedDict,
|
||||
ResponsesOutputItemReasoningTypedDict,
|
||||
],
|
||||
)
|
||||
r"""An output item from the response"""
|
||||
|
||||
@@ -9,10 +9,14 @@ from openrouter.types import (
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
UnrecognizedStr,
|
||||
)
|
||||
from openrouter.utils import validate_open_enum
|
||||
import pydantic
|
||||
from pydantic import model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Literal, Optional, Union
|
||||
from typing_extensions import NotRequired, TypeAliasType, TypedDict
|
||||
from typing_extensions import Annotated, NotRequired, TypeAliasType, TypedDict
|
||||
|
||||
|
||||
ResponsesOutputItemReasoningType = Literal["reasoning",]
|
||||
@@ -47,6 +51,20 @@ ResponsesOutputItemReasoningStatusUnion = TypeAliasType(
|
||||
)
|
||||
|
||||
|
||||
ResponsesOutputItemReasoningFormat = Union[
|
||||
Literal[
|
||||
"unknown",
|
||||
"openai-responses-v1",
|
||||
"azure-openai-responses-v1",
|
||||
"xai-responses-v1",
|
||||
"anthropic-claude-v1",
|
||||
"google-gemini-v1",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""The format of the reasoning content"""
|
||||
|
||||
|
||||
class ResponsesOutputItemReasoningTypedDict(TypedDict):
|
||||
r"""An output item containing reasoning"""
|
||||
|
||||
@@ -56,6 +74,10 @@ class ResponsesOutputItemReasoningTypedDict(TypedDict):
|
||||
content: NotRequired[List[ReasoningTextContentTypedDict]]
|
||||
encrypted_content: NotRequired[Nullable[str]]
|
||||
status: NotRequired[ResponsesOutputItemReasoningStatusUnionTypedDict]
|
||||
signature: NotRequired[Nullable[str]]
|
||||
r"""A signature for the reasoning content, used for verification"""
|
||||
format_: NotRequired[Nullable[ResponsesOutputItemReasoningFormat]]
|
||||
r"""The format of the reasoning content"""
|
||||
|
||||
|
||||
class ResponsesOutputItemReasoning(BaseModel):
|
||||
@@ -73,10 +95,28 @@ class ResponsesOutputItemReasoning(BaseModel):
|
||||
|
||||
status: Optional[ResponsesOutputItemReasoningStatusUnion] = None
|
||||
|
||||
signature: OptionalNullable[str] = UNSET
|
||||
r"""A signature for the reasoning content, used for verification"""
|
||||
|
||||
format_: Annotated[
|
||||
Annotated[
|
||||
OptionalNullable[ResponsesOutputItemReasoningFormat],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
],
|
||||
pydantic.Field(alias="format"),
|
||||
] = UNSET
|
||||
r"""The format of the reasoning content"""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["content", "encrypted_content", "status"]
|
||||
nullable_fields = ["encrypted_content"]
|
||||
optional_fields = [
|
||||
"content",
|
||||
"encrypted_content",
|
||||
"status",
|
||||
"signature",
|
||||
"format",
|
||||
]
|
||||
nullable_fields = ["encrypted_content", "signature", "format"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
@@ -0,0 +1,14 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import UnrecognizedStr
|
||||
from typing import Literal, Union
|
||||
|
||||
|
||||
ResponsesOutputModality = Union[
|
||||
Literal[
|
||||
"text",
|
||||
"image",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
Reference in New Issue
Block a user