@homeflare/distilled-litellm 0.2.0

package/src/services/model_management.ts

@@ -0,0 +1,4501 @@
+// AUTO-GENERATED by scripts/generate.ts from .generated-specs (pinned litellm-openapi @ 1.100.0 — see README). Do not edit.
+import * as S from "@distilled.cloud/core/schema";
+import * as API from "@distilled.cloud/core/api";
+import * as C from "@distilled.cloud/core/category";
+import * as T from "../traits.ts";
+import {
+  LitellmProtocol,
+  type LitellmOpError,
+  type LitellmOpContext,
+} from "../protocol.ts";
+import * as Retry from "../retry.ts";
+
+export type { LitellmOpError, LitellmOpContext };
+
+export class BadRequest
+  extends /*@__PURE__*/ T.applyErrorMatchers(
+    /*@__PURE__*/ S.TaggedError<BadRequest>()("BadRequest", {
+      code: S.Number,
+      message: S.String,
+    }).pipe(C.withBadRequestError),
+    [{ status: 400 }],
+  ) {}
+
+export class UnprocessableEntity
+  extends /*@__PURE__*/ T.applyErrorMatchers(
+    /*@__PURE__*/ S.TaggedError<UnprocessableEntity>()("UnprocessableEntity", {
+      code: S.Number,
+      message: S.String,
+    }).pipe(C.withBadRequestError),
+    [{ status: 422 }],
+  ) {}
+
+export type LiteLLMParamsAdaptiveRouterConfigMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMParamsAdaptiveRouterConfigMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsAdaptiveRouterConfigMap>;
+
+export type LiteLLMParamsBedrockTagsList = Array<unknown>;
+export const LiteLLMParamsBedrockTagsList = /*@__PURE__*/ S.Array(
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsBedrockTagsList>;
+
+export type LiteLLMParamsComplexityRouterConfigMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMParamsComplexityRouterConfigMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsComplexityRouterConfigMap>;
+
+export interface ConfigurableClientsideParamsCustomAuthInput {
+  api_base: string;
+}
+export const ConfigurableClientsideParamsCustomAuthInput =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      api_base: S.String,
+    }),
+  ).annotate({
+    identifier: "ConfigurableClientsideParamsCustomAuthInput",
+  }) as any as S.Schema<ConfigurableClientsideParamsCustomAuthInput>;
+
+export type LiteLLMParamsConfigurableClientsideAuthParamsItem =
+  | string
+  | ConfigurableClientsideParamsCustomAuthInput;
+export const LiteLLMParamsConfigurableClientsideAuthParamsItem =
+  S.Unknown as any as S.Schema<LiteLLMParamsConfigurableClientsideAuthParamsItem>;
+
+export type LiteLLMParamsConfigurableClientsideAuthParamsList =
+  Array<LiteLLMParamsConfigurableClientsideAuthParamsItem>;
+export const LiteLLMParamsConfigurableClientsideAuthParamsList =
+  /*@__PURE__*/ S.Array(
+    LiteLLMParamsConfigurableClientsideAuthParamsItem,
+  ) as any as S.Schema<LiteLLMParamsConfigurableClientsideAuthParamsList>;
+
+export type LiteLLMParamsMilvusPartitionNamesList = Array<string>;
+export const LiteLLMParamsMilvusPartitionNamesList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<LiteLLMParamsMilvusPartitionNamesList>;
+
+export type ChoicesFinishReason =
+  | "stop"
+  | "content_filter"
+  | "function_call"
+  | "tool_calls"
+  | "length"
+  | "guardrail_intervened"
+  | "eos"
+  | "finish_reason_unspecified"
+  | "malformed_function_call";
+export const ChoicesFinishReason = S.String;
+
+export type ChatCompletionTokenLogprobBytesList = Array<number>;
+export const ChatCompletionTokenLogprobBytesList = /*@__PURE__*/ S.Array(
+  S.Number,
+) as any as S.Schema<ChatCompletionTokenLogprobBytesList>;
+
+export type TopLogprobBytesList = Array<number>;
+export const TopLogprobBytesList = /*@__PURE__*/ S.Array(
+  S.Number,
+) as any as S.Schema<TopLogprobBytesList>;
+
+export interface TopLogprob {
+  bytes?: TopLogprobBytesList | null;
+  logprob: number;
+  token: string;
+}
+export const TopLogprob = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    bytes: S.optional(S.NullOr(TopLogprobBytesList)),
+    logprob: S.Number,
+    token: S.String,
+  }),
+).annotate({ identifier: "TopLogprob" }) as any as S.Schema<TopLogprob>;
+
+export type ChatCompletionTokenLogprobTopLogprobsList = Array<TopLogprob>;
+export const ChatCompletionTokenLogprobTopLogprobsList = /*@__PURE__*/ S.Array(
+  TopLogprob,
+) as any as S.Schema<ChatCompletionTokenLogprobTopLogprobsList>;
+
+export interface ChatCompletionTokenLogprob {
+  bytes?: ChatCompletionTokenLogprobBytesList | null;
+  logprob: number;
+  token: string;
+  top_logprobs: ChatCompletionTokenLogprobTopLogprobsList;
+}
+export const ChatCompletionTokenLogprob = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    bytes: S.optional(S.NullOr(ChatCompletionTokenLogprobBytesList)),
+    logprob: S.Number,
+    token: S.String,
+    top_logprobs: ChatCompletionTokenLogprobTopLogprobsList,
+  }),
+).annotate({
+  identifier: "ChatCompletionTokenLogprob",
+}) as any as S.Schema<ChatCompletionTokenLogprob>;
+
+export type ChoiceLogprobsContentList = Array<ChatCompletionTokenLogprob>;
+export const ChoiceLogprobsContentList = /*@__PURE__*/ S.Array(
+  ChatCompletionTokenLogprob,
+) as any as S.Schema<ChoiceLogprobsContentList>;
+
+export interface ChoiceLogprobs {
+  content?: ChoiceLogprobsContentList | null;
+}
+export const ChoiceLogprobs = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    content: S.optional(S.NullOr(ChoiceLogprobsContentList)),
+  }),
+).annotate({ identifier: "ChoiceLogprobs" }) as any as S.Schema<ChoiceLogprobs>;
+
+export type ChoicesLogprobs = ChoiceLogprobs | unknown;
+export const ChoicesLogprobs = S.Unknown as any as S.Schema<ChoicesLogprobs>;
+
+export interface ChatCompletionAnnotationURLCitation {
+  end_index?: number;
+  start_index?: number;
+  title?: string;
+  url?: string;
+}
+export const ChatCompletionAnnotationURLCitation = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    end_index: S.optional(S.Number),
+    start_index: S.optional(S.Number),
+    title: S.optional(S.String),
+    url: S.optional(S.String),
+  }),
+).annotate({
+  identifier: "ChatCompletionAnnotationURLCitation",
+}) as any as S.Schema<ChatCompletionAnnotationURLCitation>;
+
+export interface ChatCompletionAnnotation {
+  type?: string;
+  url_citation?: ChatCompletionAnnotationURLCitation;
+}
+export const ChatCompletionAnnotation = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    type: S.optional(S.String),
+    url_citation: S.optional(ChatCompletionAnnotationURLCitation),
+  }),
+).annotate({
+  identifier: "ChatCompletionAnnotation",
+}) as any as S.Schema<ChatCompletionAnnotation>;
+
+export type MessageAnnotationsList = Array<ChatCompletionAnnotation>;
+export const MessageAnnotationsList = /*@__PURE__*/ S.Array(
+  ChatCompletionAnnotation,
+) as any as S.Schema<MessageAnnotationsList>;
+
+export interface ChatCompletionAudioResponse {
+  data: string;
+  expires_at: number;
+  id: string;
+  transcript: string;
+}
+export const ChatCompletionAudioResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    data: S.String,
+    expires_at: S.Number,
+    id: S.String,
+    transcript: S.String,
+  }),
+).annotate({
+  identifier: "ChatCompletionAudioResponse",
+}) as any as S.Schema<ChatCompletionAudioResponse>;
+
+export interface FunctionCall {
+  arguments: string;
+  name?: string | null;
+}
+export const FunctionCall = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    arguments: S.String,
+    name: S.optional(S.NullOr(S.String)),
+  }),
+).annotate({ identifier: "FunctionCall" }) as any as S.Schema<FunctionCall>;
+
+export interface ImageURLObject {
+  detail?: string | null;
+  url: string;
+}
+export const ImageURLObject = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    detail: S.optional(S.NullOr(S.String)),
+    url: S.String,
+  }),
+).annotate({ identifier: "ImageURLObject" }) as any as S.Schema<ImageURLObject>;
+
+export interface ImageURLListItem {
+  image_url: ImageURLObject;
+  index: number;
+  type: string;
+}
+export const ImageURLListItem = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    image_url: ImageURLObject,
+    index: S.Number,
+    type: S.String,
+  }),
+).annotate({
+  identifier: "ImageURLListItem",
+}) as any as S.Schema<ImageURLListItem>;
+
+export type MessageImagesList = Array<ImageURLListItem>;
+export const MessageImagesList = /*@__PURE__*/ S.Array(
+  ImageURLListItem,
+) as any as S.Schema<MessageImagesList>;
+
+export type MessageProviderSpecificFieldsMap = {
+  [key: string]: unknown | undefined;
+};
+export const MessageProviderSpecificFieldsMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<MessageProviderSpecificFieldsMap>;
+
+export interface ChatCompletionReasoningSummaryTextBlock {
+  text?: string;
+  type: string;
+}
+export const ChatCompletionReasoningSummaryTextBlock = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      text: S.optional(S.String),
+      type: S.String,
+    }),
+).annotate({
+  identifier: "ChatCompletionReasoningSummaryTextBlock",
+}) as any as S.Schema<ChatCompletionReasoningSummaryTextBlock>;
+
+export type ChatCompletionReasoningItemSummaryList =
+  Array<ChatCompletionReasoningSummaryTextBlock>;
+export const ChatCompletionReasoningItemSummaryList = /*@__PURE__*/ S.Array(
+  ChatCompletionReasoningSummaryTextBlock,
+) as any as S.Schema<ChatCompletionReasoningItemSummaryList>;
+
+/** Represents an OpenAI Responses API reasoning item for round-tripping in conversation history. */
+export interface ChatCompletionReasoningItem {
+  encrypted_content?: string | null;
+  id?: string;
+  summary?: ChatCompletionReasoningItemSummaryList;
+  type: string;
+}
+export const ChatCompletionReasoningItem = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    encrypted_content: S.optional(S.NullOr(S.String)),
+    id: S.optional(S.String),
+    summary: S.optional(ChatCompletionReasoningItemSummaryList),
+    type: S.String,
+  }),
+).annotate({
+  identifier: "ChatCompletionReasoningItem",
+}) as any as S.Schema<ChatCompletionReasoningItem>;
+
+export type MessageReasoningItemsList = Array<ChatCompletionReasoningItem>;
+export const MessageReasoningItemsList = /*@__PURE__*/ S.Array(
+  ChatCompletionReasoningItem,
+) as any as S.Schema<MessageReasoningItemsList>;
+
+export type MessageRole = "assistant" | "user" | "system" | "tool" | "function";
+export const MessageRole = S.String;
+
+export type ChatCompletionThinkingBlockCacheControlCase0Map = {
+  [key: string]: unknown | undefined;
+};
+export const ChatCompletionThinkingBlockCacheControlCase0Map =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<ChatCompletionThinkingBlockCacheControlCase0Map>;
+
+export type ChatCompletionCachedContentTtl = "5m" | "1h";
+export const ChatCompletionCachedContentTtl = S.String;
+
+export interface ChatCompletionCachedContent {
+  ttl?: ChatCompletionCachedContentTtl | (string & {});
+  type: string;
+}
+export const ChatCompletionCachedContent = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    ttl: S.optional(ChatCompletionCachedContentTtl),
+    type: S.String,
+  }),
+).annotate({
+  identifier: "ChatCompletionCachedContent",
+}) as any as S.Schema<ChatCompletionCachedContent>;
+
+export type ChatCompletionThinkingBlockCacheControl =
+  | ChatCompletionThinkingBlockCacheControlCase0Map
+  | ChatCompletionCachedContent;
+export const ChatCompletionThinkingBlockCacheControl =
+  S.Unknown as any as S.Schema<ChatCompletionThinkingBlockCacheControl>;
+
+export interface ChatCompletionThinkingBlock {
+  cache_control?: ChatCompletionThinkingBlockCacheControl | null;
+  signature?: string | null;
+  thinking?: string;
+  type: string;
+}
+export const ChatCompletionThinkingBlock = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    cache_control: S.optional(
+      S.NullOr(ChatCompletionThinkingBlockCacheControl),
+    ),
+    signature: S.optional(S.NullOr(S.String)),
+    thinking: S.optional(S.String),
+    type: S.String,
+  }),
+).annotate({
+  identifier: "ChatCompletionThinkingBlock",
+}) as any as S.Schema<ChatCompletionThinkingBlock>;
+
+export type ChatCompletionRedactedThinkingBlockCacheControlCase0Map = {
+  [key: string]: unknown | undefined;
+};
+export const ChatCompletionRedactedThinkingBlockCacheControlCase0Map =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<ChatCompletionRedactedThinkingBlockCacheControlCase0Map>;
+
+export type ChatCompletionRedactedThinkingBlockCacheControl =
+  | ChatCompletionRedactedThinkingBlockCacheControlCase0Map
+  | ChatCompletionCachedContent;
+export const ChatCompletionRedactedThinkingBlockCacheControl =
+  S.Unknown as any as S.Schema<ChatCompletionRedactedThinkingBlockCacheControl>;
+
+export interface ChatCompletionRedactedThinkingBlock {
+  cache_control?: ChatCompletionRedactedThinkingBlockCacheControl | null;
+  data?: string;
+  type: string;
+}
+export const ChatCompletionRedactedThinkingBlock = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    cache_control: S.optional(
+      S.NullOr(ChatCompletionRedactedThinkingBlockCacheControl),
+    ),
+    data: S.optional(S.String),
+    type: S.String,
+  }),
+).annotate({
+  identifier: "ChatCompletionRedactedThinkingBlock",
+}) as any as S.Schema<ChatCompletionRedactedThinkingBlock>;
+
+export type MessageThinkingBlocksItem =
+  | ChatCompletionThinkingBlock
+  | ChatCompletionRedactedThinkingBlock;
+export const MessageThinkingBlocksItem =
+  S.Unknown as any as S.Schema<MessageThinkingBlocksItem>;
+
+export type MessageThinkingBlocksList = Array<MessageThinkingBlocksItem>;
+export const MessageThinkingBlocksList = /*@__PURE__*/ S.Array(
+  MessageThinkingBlocksItem,
+) as any as S.Schema<MessageThinkingBlocksList>;
+
+export type ChatCompletionMessageToolCall = {
+  [key: string]: unknown | undefined;
+};
+export const ChatCompletionMessageToolCall = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<ChatCompletionMessageToolCall>;
+
+export interface ChatCompletionCustomToolCallPayload {
+  input: string;
+  name: string;
+}
+export const ChatCompletionCustomToolCallPayload = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    input: S.String,
+    name: S.String,
+  }),
+).annotate({
+  identifier: "ChatCompletionCustomToolCallPayload",
+}) as any as S.Schema<ChatCompletionCustomToolCallPayload>;
+
+export interface ChatCompletionMessageCustomToolCall {
+  custom: ChatCompletionCustomToolCallPayload;
+  id: string;
+  type?: string;
+}
+export const ChatCompletionMessageCustomToolCall = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    custom: ChatCompletionCustomToolCallPayload,
+    id: S.String,
+    type: S.optional(S.String),
+  }),
+).annotate({
+  identifier: "ChatCompletionMessageCustomToolCall",
+}) as any as S.Schema<ChatCompletionMessageCustomToolCall>;
+
+export type MessageToolCallsItem =
+  | ChatCompletionMessageToolCall
+  | ChatCompletionMessageCustomToolCall;
+export const MessageToolCallsItem =
+  S.Unknown as any as S.Schema<MessageToolCallsItem>;
+
+export type MessageToolCallsList = Array<MessageToolCallsItem>;
+export const MessageToolCallsList = /*@__PURE__*/ S.Array(
+  MessageToolCallsItem,
+) as any as S.Schema<MessageToolCallsList>;
+
+export interface Message {
+  annotations?: MessageAnnotationsList | null;
+  audio?: ChatCompletionAudioResponse | null;
+  content: string | null;
+  function_call: FunctionCall | null;
+  images?: MessageImagesList | null;
+  provider_specific_fields?: MessageProviderSpecificFieldsMap | null;
+  reasoning_content?: string | null;
+  reasoning_items?: MessageReasoningItemsList | null;
+  role: MessageRole | (string & {});
+  thinking_blocks?: MessageThinkingBlocksList | null;
+  tool_calls: MessageToolCallsList | null;
+}
+export const Message = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    annotations: S.optional(S.NullOr(MessageAnnotationsList)),
+    audio: S.optional(S.NullOr(ChatCompletionAudioResponse)),
+    content: S.NullOr(S.String),
+    function_call: S.NullOr(FunctionCall),
+    images: S.optional(S.NullOr(MessageImagesList)),
+    provider_specific_fields: S.optional(
+      S.NullOr(MessageProviderSpecificFieldsMap),
+    ),
+    reasoning_content: S.optional(S.NullOr(S.String)),
+    reasoning_items: S.optional(S.NullOr(MessageReasoningItemsList)),
+    role: MessageRole,
+    thinking_blocks: S.optional(S.NullOr(MessageThinkingBlocksList)),
+    tool_calls: S.NullOr(MessageToolCallsList),
+  }),
+).annotate({ identifier: "Message" }) as any as S.Schema<Message>;
+
+export type ChoicesProviderSpecificFieldsMap = {
+  [key: string]: unknown | undefined;
+};
+export const ChoicesProviderSpecificFieldsMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<ChoicesProviderSpecificFieldsMap>;
+
+export interface Choices {
+  finish_reason: ChoicesFinishReason | (string & {});
+  index: number;
+  logprobs?: ChoicesLogprobs | null;
+  message: Message;
+  provider_specific_fields?: ChoicesProviderSpecificFieldsMap | null;
+}
+export const Choices = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    finish_reason: ChoicesFinishReason,
+    index: S.Number,
+    logprobs: S.optional(S.NullOr(ChoicesLogprobs)),
+    message: Message,
+    provider_specific_fields: S.optional(
+      S.NullOr(ChoicesProviderSpecificFieldsMap),
+    ),
+  }),
+).annotate({ identifier: "Choices" }) as any as S.Schema<Choices>;
+
+export type ModelResponseChoicesList = Array<Choices>;
+export const ModelResponseChoicesList = /*@__PURE__*/ S.Array(
+  Choices,
+) as any as S.Schema<ModelResponseChoicesList>;
+
+export interface ModelResponse {
+  choices: ModelResponseChoicesList;
+  created: number;
+  id: string;
+  model?: string | null;
+  object: string;
+  system_fingerprint?: string | null;
+}
+export const ModelResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    choices: ModelResponseChoicesList,
+    created: S.Number,
+    id: S.String,
+    model: S.optional(S.NullOr(S.String)),
+    object: S.String,
+    system_fingerprint: S.optional(S.NullOr(S.String)),
+  }),
+).annotate({ identifier: "ModelResponse" }) as any as S.Schema<ModelResponse>;
+
+export type LiteLLMParamsMockResponse = string | ModelResponse | unknown;
+export const LiteLLMParamsMockResponse =
+  S.Unknown as any as S.Schema<LiteLLMParamsMockResponse>;
+
+export type LiteLLMParamsModelInfoMap = { [key: string]: unknown | undefined };
+export const LiteLLMParamsModelInfoMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsModelInfoMap>;
+
+export type LiteLLMParamsQualityRouterConfigMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMParamsQualityRouterConfigMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsQualityRouterConfigMap>;
+
+export type LiteLLMParamsSearchContextCostPerQueryMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMParamsSearchContextCostPerQueryMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsSearchContextCostPerQueryMap>;
+
+export type LiteLLMParamsStreamTimeout = number | string;
+export const LiteLLMParamsStreamTimeout =
+  S.Unknown as any as S.Schema<LiteLLMParamsStreamTimeout>;
+
+export type LiteLLMParamsTagRegexList = Array<string>;
+export const LiteLLMParamsTagRegexList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<LiteLLMParamsTagRegexList>;
+
+export type LiteLLMParamsTagsList = Array<string>;
+export const LiteLLMParamsTagsList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<LiteLLMParamsTagsList>;
+
+export type LiteLLMParamsTieredPricingItemMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMParamsTieredPricingItemMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsTieredPricingItemMap>;
+
+export type LiteLLMParamsTieredPricingList =
+  Array<LiteLLMParamsTieredPricingItemMap>;
+export const LiteLLMParamsTieredPricingList = /*@__PURE__*/ S.Array(
+  LiteLLMParamsTieredPricingItemMap,
+) as any as S.Schema<LiteLLMParamsTieredPricingList>;
+
+export type LiteLLMParamsTimeout = number | string;
+export const LiteLLMParamsTimeout =
+  S.Unknown as any as S.Schema<LiteLLMParamsTimeout>;
+
+export type LiteLLMParamsVertexCredentialsCase1Map = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMParamsVertexCredentialsCase1Map = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMParamsVertexCredentialsCase1Map>;
+
+export type LiteLLMParamsVertexCredentials =
+  | string
+  | LiteLLMParamsVertexCredentialsCase1Map;
+export const LiteLLMParamsVertexCredentials =
+  S.Unknown as any as S.Schema<LiteLLMParamsVertexCredentials>;
+
+/** LiteLLM Params with 'model' requirement - used for completions */
+export interface LiteLLMParams {
+  adaptive_router_config?: LiteLLMParamsAdaptiveRouterConfigMap | null;
+  adaptive_router_default_model?: string | null;
+  allow_client_keepalive_override?: boolean | null;
+  annotation_cost_per_page?: number | null;
+  api_base?: string | null;
+  api_key?: string | null;
+  api_version?: string | null;
+  auto_router_config?: string | null;
+  auto_router_config_path?: string | null;
+  auto_router_default_model?: string | null;
+  auto_router_embedding_model?: string | null;
+  auto_router_max_input_chars?: number | null;
+  aws_access_key_id?: string | null;
+  aws_batch_role_arn?: string | null;
+  aws_bedrock_project_id?: string | null;
+  aws_bedrock_runtime_endpoint?: string | null;
+  aws_external_id?: string | null;
+  aws_profile_name?: string | null;
+  aws_region_name?: string | null;
+  aws_role_name?: string | null;
+  aws_secret_access_key?: string | null;
+  aws_session_name?: string | null;
+  aws_session_token?: string | null;
+  aws_sts_endpoint?: string | null;
+  aws_web_identity_token?: string | null;
+  azure_ad_token?: string | null;
+  bedrock_tags?: LiteLLMParamsBedrockTagsList | null;
+  budget_duration?: string | null;
+  cache_creation_input_audio_token_cost?: number | null;
+  cache_creation_input_token_cost?: number | null;
+  cache_creation_input_token_cost_above_1hr?: number | null;
+  cache_creation_input_token_cost_above_200k_tokens?: number | null;
+  cache_creation_input_token_cost_above_272k_tokens?: number | null;
+  cache_creation_input_token_cost_above_272k_tokens_flex?: number | null;
+  cache_creation_input_token_cost_above_272k_tokens_priority?: number | null;
+  cache_creation_input_token_cost_flex?: number | null;
+  cache_creation_input_token_cost_priority?: number | null;
+  cache_creation_input_token_cost_ultrafast?: number | null;
+  cache_read_input_audio_token_cost?: number | null;
+  cache_read_input_token_cost?: number | null;
+  cache_read_input_token_cost_above_200k_tokens?: number | null;
+  cache_read_input_token_cost_above_200k_tokens_priority?: number | null;
+  cache_read_input_token_cost_above_272k_tokens?: number | null;
+  cache_read_input_token_cost_above_272k_tokens_flex?: number | null;
+  cache_read_input_token_cost_above_272k_tokens_priority?: number | null;
+  cache_read_input_token_cost_above_512k_tokens?: number | null;
+  cache_read_input_token_cost_flex?: number | null;
+  cache_read_input_token_cost_priority?: number | null;
+  cache_read_input_token_cost_ultrafast?: number | null;
+  citation_cost_per_token?: number | null;
+  complexity_router_config?: LiteLLMParamsComplexityRouterConfigMap | null;
+  complexity_router_default_model?: string | null;
+  configurable_clientside_auth_params?: LiteLLMParamsConfigurableClientsideAuthParamsList | null;
+  custom_llm_provider?: string | null;
+  default_api_key_rpm_limit?: number | null;
+  default_api_key_tpm_limit?: number | null;
+  gcs_bucket_name?: string | null;
+  google_maps_grounding_cost_per_query?: number | null;
+  input_cost_per_audio_per_second?: number | null;
+  input_cost_per_audio_per_second_above_128k_tokens?: number | null;
+  input_cost_per_audio_token?: number | null;
+  input_cost_per_character?: number | null;
+  input_cost_per_character_above_128k_tokens?: number | null;
+  input_cost_per_image?: number | null;
+  input_cost_per_image_above_128k_tokens?: number | null;
+  input_cost_per_image_token?: number | null;
+  input_cost_per_pixel?: number | null;
+  input_cost_per_query?: number | null;
+  input_cost_per_second?: number | null;
+  input_cost_per_token?: number | null;
+  input_cost_per_token_above_128k_tokens?: number | null;
+  input_cost_per_token_above_200k_tokens?: number | null;
+  input_cost_per_token_above_200k_tokens_priority?: number | null;
+  input_cost_per_token_above_272k_tokens?: number | null;
+  input_cost_per_token_above_272k_tokens_flex?: number | null;
+  input_cost_per_token_above_272k_tokens_priority?: number | null;
+  input_cost_per_token_above_512k_tokens?: number | null;
+  input_cost_per_token_batches?: number | null;
+  input_cost_per_token_cache_hit?: number | null;
+  input_cost_per_token_flex?: number | null;
+  input_cost_per_token_priority?: number | null;
+  input_cost_per_token_ultrafast?: number | null;
+  input_cost_per_video_per_second?: number | null;
+  input_cost_per_video_per_second_above_128k_tokens?: number | null;
+  input_cost_per_video_per_second_above_15s_interval?: number | null;
+  input_cost_per_video_per_second_above_8s_interval?: number | null;
+  input_cost_per_video_token?: number | null;
+  itpm?: number | null;
+  keepalive_seconds?: number | null;
+  litellm_credential_name?: string | null;
+  litellm_trace_id?: string | null;
+  max_budget?: number | null;
+  max_file_size_mb?: number | null;
+  max_retries?: number | null;
+  merge_reasoning_content_in_choices?: boolean | null;
+  milvus_db_name?: string | null;
+  milvus_partition_names?: LiteLLMParamsMilvusPartitionNamesList | null;
+  milvus_text_field?: string | null;
+  mock_response?: LiteLLMParamsMockResponse | null;
+  model: string;
+  model_info?: LiteLLMParamsModelInfoMap | null;
+  ocr_cost_per_credit?: number | null;
+  ocr_cost_per_page?: number | null;
+  organization?: string | null;
+  otpm?: number | null;
+  output_cost_per_audio_per_second?: number | null;
+  output_cost_per_audio_token?: number | null;
+  output_cost_per_character?: number | null;
+  output_cost_per_character_above_128k_tokens?: number | null;
+  output_cost_per_image?: number | null;
+  output_cost_per_image_token?: number | null;
+  output_cost_per_pixel?: number | null;
+  output_cost_per_reasoning_token?: number | null;
+  output_cost_per_reasoning_token_flex?: number | null;
+  output_cost_per_reasoning_token_priority?: number | null;
+  output_cost_per_second?: number | null;
+  output_cost_per_second_1080p?: number | null;
+  output_cost_per_second_480p?: number | null;
+  output_cost_per_second_4k?: number | null;
+  output_cost_per_token?: number | null;
+  output_cost_per_token_above_128k_tokens?: number | null;
+  output_cost_per_token_above_200k_tokens?: number | null;
+  output_cost_per_token_above_200k_tokens_priority?: number | null;
+  output_cost_per_token_above_272k_tokens?: number | null;
+  output_cost_per_token_above_272k_tokens_flex?: number | null;
+  output_cost_per_token_above_272k_tokens_priority?: number | null;
+  output_cost_per_token_above_512k_tokens?: number | null;
+  output_cost_per_token_batches?: number | null;
+  output_cost_per_token_flex?: number | null;
+  output_cost_per_token_priority?: number | null;
+  output_cost_per_token_ultrafast?: number | null;
+  output_cost_per_video_per_second?: number | null;
+  output_cost_per_video_token?: number | null;
+  output_vector_size?: number | null;
+  quality_router_config?: LiteLLMParamsQualityRouterConfigMap | null;
+  quality_router_default_model?: string | null;
+  region_name?: string | null;
+  regional_endpoint_uplift_multiplier?: number | null;
+  regional_processing_uplift_multiplier_eu?: number | null;
+  regional_processing_uplift_multiplier_us?: number | null;
+  rpm?: number | null;
+  s3_bucket_name?: string | null;
+  s3_encryption_key_id?: string | null;
+  s3_output_bucket_name?: string | null;
+  s3_region_name?: string | null;
+  search_context_cost_per_query?: LiteLLMParamsSearchContextCostPerQueryMap | null;
+  stream_timeout?: LiteLLMParamsStreamTimeout | null;
+  tag_regex?: LiteLLMParamsTagRegexList | null;
+  tags?: LiteLLMParamsTagsList | null;
+  tiered_pricing?: LiteLLMParamsTieredPricingList | null;
+  timeout?: LiteLLMParamsTimeout | null;
+  tpm?: number | null;
+  use_chat_completions_api?: boolean | null;
+  use_in_pass_through?: boolean | null;
+  use_litellm_proxy?: boolean | null;
+  /** Use stored xAI OAuth credentials when no xAI API key is configured. */
+  use_xai_oauth?: boolean | null;
+  valkey_embedding_field?: string | null;
+  valkey_host?: string | null;
+  valkey_password?: string | null;
+  valkey_port?: number | null;
+  valkey_ssl?: boolean | null;
+  valkey_text_field?: string | null;
+  vector_store_id?: string | null;
+  vertex_credentials?: LiteLLMParamsVertexCredentials | null;
+  vertex_location?: string | null;
+  vertex_project?: string | null;
+  watsonx_region_name?: string | null;
+}
+export const LiteLLMParams = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    adaptive_router_config: S.optional(
+      S.NullOr(LiteLLMParamsAdaptiveRouterConfigMap),
+    ),
+    adaptive_router_default_model: S.optional(S.NullOr(S.String)),
+    allow_client_keepalive_override: S.optional(S.NullOr(S.Boolean)),
+    annotation_cost_per_page: S.optional(S.NullOr(S.Number)),
+    api_base: S.optional(S.NullOr(S.String)),
+    api_key: S.optional(S.NullOr(S.String)),
+    api_version: S.optional(S.NullOr(S.String)),
+    auto_router_config: S.optional(S.NullOr(S.String)),
+    auto_router_config_path: S.optional(S.NullOr(S.String)),
+    auto_router_default_model: S.optional(S.NullOr(S.String)),
+    auto_router_embedding_model: S.optional(S.NullOr(S.String)),
+    auto_router_max_input_chars: S.optional(S.NullOr(S.Number)),
+    aws_access_key_id: S.optional(S.NullOr(S.String)),
+    aws_batch_role_arn: S.optional(S.NullOr(S.String)),
+    aws_bedrock_project_id: S.optional(S.NullOr(S.String)),
+    aws_bedrock_runtime_endpoint: S.optional(S.NullOr(S.String)),
+    aws_external_id: S.optional(S.NullOr(S.String)),
+    aws_profile_name: S.optional(S.NullOr(S.String)),
+    aws_region_name: S.optional(S.NullOr(S.String)),
+    aws_role_name: S.optional(S.NullOr(S.String)),
+    aws_secret_access_key: S.optional(S.NullOr(S.String)),
+    aws_session_name: S.optional(S.NullOr(S.String)),
+    aws_session_token: S.optional(S.NullOr(S.String)),
+    aws_sts_endpoint: S.optional(S.NullOr(S.String)),
+    aws_web_identity_token: S.optional(S.NullOr(S.String)),
+    azure_ad_token: S.optional(S.NullOr(S.String)),
+    bedrock_tags: S.optional(S.NullOr(LiteLLMParamsBedrockTagsList)),
+    budget_duration: S.optional(S.NullOr(S.String)),
+    cache_creation_input_audio_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_above_1hr: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_above_200k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_above_272k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_above_272k_tokens_flex: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_flex: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_priority: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_ultrafast: S.optional(S.NullOr(S.Number)),
+    cache_read_input_audio_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost_above_200k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_200k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_272k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_272k_tokens_flex: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_512k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_flex: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost_priority: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost_ultrafast: S.optional(S.NullOr(S.Number)),
+    citation_cost_per_token: S.optional(S.NullOr(S.Number)),
+    complexity_router_config: S.optional(
+      S.NullOr(LiteLLMParamsComplexityRouterConfigMap),
+    ),
+    complexity_router_default_model: S.optional(S.NullOr(S.String)),
+    configurable_clientside_auth_params: S.optional(
+      S.NullOr(LiteLLMParamsConfigurableClientsideAuthParamsList),
+    ),
+    custom_llm_provider: S.optional(S.NullOr(S.String)),
+    default_api_key_rpm_limit: S.optional(S.NullOr(S.Number)),
+    default_api_key_tpm_limit: S.optional(S.NullOr(S.Number)),
+    gcs_bucket_name: S.optional(S.NullOr(S.String)),
+    google_maps_grounding_cost_per_query: S.optional(S.NullOr(S.Number)),
+    input_cost_per_audio_per_second: S.optional(S.NullOr(S.Number)),
+    input_cost_per_audio_per_second_above_128k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_audio_token: S.optional(S.NullOr(S.Number)),
+    input_cost_per_character: S.optional(S.NullOr(S.Number)),
+    input_cost_per_character_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_image: S.optional(S.NullOr(S.Number)),
+    input_cost_per_image_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_image_token: S.optional(S.NullOr(S.Number)),
+    input_cost_per_pixel: S.optional(S.NullOr(S.Number)),
+    input_cost_per_query: S.optional(S.NullOr(S.Number)),
+    input_cost_per_second: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_200k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_200k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_token_above_272k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_272k_tokens_flex: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_token_above_512k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_batches: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_cache_hit: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_flex: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_priority: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_ultrafast: S.optional(S.NullOr(S.Number)),
+    input_cost_per_video_per_second: S.optional(S.NullOr(S.Number)),
+    input_cost_per_video_per_second_above_128k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_video_per_second_above_15s_interval: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_video_per_second_above_8s_interval: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_video_token: S.optional(S.NullOr(S.Number)),
+    itpm: S.optional(S.NullOr(S.Number)),
+    keepalive_seconds: S.optional(S.NullOr(S.Number)),
+    litellm_credential_name: S.optional(S.NullOr(S.String)),
+    litellm_trace_id: S.optional(S.NullOr(S.String)),
+    max_budget: S.optional(S.NullOr(S.Number)),
+    max_file_size_mb: S.optional(S.NullOr(S.Number)),
+    max_retries: S.optional(S.NullOr(S.Number)),
+    merge_reasoning_content_in_choices: S.optional(S.NullOr(S.Boolean)),
+    milvus_db_name: S.optional(S.NullOr(S.String)),
+    milvus_partition_names: S.optional(
+      S.NullOr(LiteLLMParamsMilvusPartitionNamesList),
+    ),
+    milvus_text_field: S.optional(S.NullOr(S.String)),
+    mock_response: S.optional(S.NullOr(LiteLLMParamsMockResponse)),
+    model: S.String,
+    model_info: S.optional(S.NullOr(LiteLLMParamsModelInfoMap)),
+    ocr_cost_per_credit: S.optional(S.NullOr(S.Number)),
+    ocr_cost_per_page: S.optional(S.NullOr(S.Number)),
+    organization: S.optional(S.NullOr(S.String)),
+    otpm: S.optional(S.NullOr(S.Number)),
+    output_cost_per_audio_per_second: S.optional(S.NullOr(S.Number)),
+    output_cost_per_audio_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_character: S.optional(S.NullOr(S.Number)),
+    output_cost_per_character_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_image: S.optional(S.NullOr(S.Number)),
+    output_cost_per_image_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_pixel: S.optional(S.NullOr(S.Number)),
+    output_cost_per_reasoning_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_reasoning_token_flex: S.optional(S.NullOr(S.Number)),
+    output_cost_per_reasoning_token_priority: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second_1080p: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second_480p: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second_4k: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_200k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_200k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    output_cost_per_token_above_272k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_272k_tokens_flex: S.optional(
+      S.NullOr(S.Number),
+    ),
+    output_cost_per_token_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    output_cost_per_token_above_512k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_batches: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_flex: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_priority: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_ultrafast: S.optional(S.NullOr(S.Number)),
+    output_cost_per_video_per_second: S.optional(S.NullOr(S.Number)),
+    output_cost_per_video_token: S.optional(S.NullOr(S.Number)),
+    output_vector_size: S.optional(S.NullOr(S.Number)),
+    quality_router_config: S.optional(
+      S.NullOr(LiteLLMParamsQualityRouterConfigMap),
+    ),
+    quality_router_default_model: S.optional(S.NullOr(S.String)),
+    region_name: S.optional(S.NullOr(S.String)),
+    regional_endpoint_uplift_multiplier: S.optional(S.NullOr(S.Number)),
+    regional_processing_uplift_multiplier_eu: S.optional(S.NullOr(S.Number)),
+    regional_processing_uplift_multiplier_us: S.optional(S.NullOr(S.Number)),
+    rpm: S.optional(S.NullOr(S.Number)),
+    s3_bucket_name: S.optional(S.NullOr(S.String)),
+    s3_encryption_key_id: S.optional(S.NullOr(S.String)),
+    s3_output_bucket_name: S.optional(S.NullOr(S.String)),
+    s3_region_name: S.optional(S.NullOr(S.String)),
+    search_context_cost_per_query: S.optional(
+      S.NullOr(LiteLLMParamsSearchContextCostPerQueryMap),
+    ),
+    stream_timeout: S.optional(S.NullOr(LiteLLMParamsStreamTimeout)),
+    tag_regex: S.optional(S.NullOr(LiteLLMParamsTagRegexList)),
+    tags: S.optional(S.NullOr(LiteLLMParamsTagsList)),
+    tiered_pricing: S.optional(S.NullOr(LiteLLMParamsTieredPricingList)),
+    timeout: S.optional(S.NullOr(LiteLLMParamsTimeout)),
+    tpm: S.optional(S.NullOr(S.Number)),
+    use_chat_completions_api: S.optional(S.NullOr(S.Boolean)),
+    use_in_pass_through: S.optional(S.NullOr(S.Boolean)),
+    use_litellm_proxy: S.optional(S.NullOr(S.Boolean)),
+    use_xai_oauth: S.optional(S.NullOr(S.Boolean)),
+    valkey_embedding_field: S.optional(S.NullOr(S.String)),
+    valkey_host: S.optional(S.NullOr(S.String)),
+    valkey_password: S.optional(S.NullOr(S.String)),
+    valkey_port: S.optional(S.NullOr(S.Number)),
+    valkey_ssl: S.optional(S.NullOr(S.Boolean)),
+    valkey_text_field: S.optional(S.NullOr(S.String)),
+    vector_store_id: S.optional(S.NullOr(S.String)),
+    vertex_credentials: S.optional(S.NullOr(LiteLLMParamsVertexCredentials)),
+    vertex_location: S.optional(S.NullOr(S.String)),
+    vertex_project: S.optional(S.NullOr(S.String)),
+    watsonx_region_name: S.optional(S.NullOr(S.String)),
+  }),
+).annotate({ identifier: "LiteLLMParams" }) as any as S.Schema<LiteLLMParams>;
+
+export type LitellmTypesRouterModelInfoTier = "free" | "paid";
+export const LitellmTypesRouterModelInfoTier = S.String;
+
+export type LitellmTypesRouterModelInfoTieredPricingItemMap = {
+  [key: string]: unknown | undefined;
+};
+export const LitellmTypesRouterModelInfoTieredPricingItemMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<LitellmTypesRouterModelInfoTieredPricingItemMap>;
+
+export type LitellmTypesRouterModelInfoTieredPricingList =
+  Array<LitellmTypesRouterModelInfoTieredPricingItemMap>;
+export const LitellmTypesRouterModelInfoTieredPricingList =
+  /*@__PURE__*/ S.Array(
+    LitellmTypesRouterModelInfoTieredPricingItemMap,
+  ) as any as S.Schema<LitellmTypesRouterModelInfoTieredPricingList>;
+
+export interface LitellmTypesRouterModelInfo {
+  allow_fail_open?: boolean | null;
+  base_model?: string | null;
+  blocked?: boolean | null;
+  cache_creation_input_token_cost?: number | null;
+  cache_read_input_token_cost?: number | null;
+  cost_per_ptu_per_hour?: number | null;
+  created_at?: string | null;
+  created_by?: string | null;
+  db_model?: boolean;
+  enable_tag_filtering?: boolean | null;
+  id: string | null;
+  input_cost_per_character?: number | null;
+  input_cost_per_token?: number | null;
+  output_cost_per_character?: number | null;
+  output_cost_per_token?: number | null;
+  ptu_count?: number | null;
+  ptu_effective_from?: string | null;
+  ptu_effective_to?: string | null;
+  team_id?: string | null;
+  team_public_model_name?: string | null;
+  tier?: LitellmTypesRouterModelInfoTier | (string & {}) | null;
+  tiered_pricing?: LitellmTypesRouterModelInfoTieredPricingList | null;
+  updated_at?: string | null;
+  updated_by?: string | null;
+}
+export const LitellmTypesRouterModelInfo = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    allow_fail_open: S.optional(S.NullOr(S.Boolean)),
+    base_model: S.optional(S.NullOr(S.String)),
+    blocked: S.optional(S.NullOr(S.Boolean)),
+    cache_creation_input_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost: S.optional(S.NullOr(S.Number)),
+    cost_per_ptu_per_hour: S.optional(S.NullOr(S.Number)),
+    created_at: S.optional(S.NullOr(S.String)),
+    created_by: S.optional(S.NullOr(S.String)),
+    db_model: S.optional(S.Boolean),
+    enable_tag_filtering: S.optional(S.NullOr(S.Boolean)),
+    id: S.NullOr(S.String),
+    input_cost_per_character: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_character: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token: S.optional(S.NullOr(S.Number)),
+    ptu_count: S.optional(S.NullOr(S.Number)),
+    ptu_effective_from: S.optional(S.NullOr(S.String)),
+    ptu_effective_to: S.optional(S.NullOr(S.String)),
+    team_id: S.optional(S.NullOr(S.String)),
+    team_public_model_name: S.optional(S.NullOr(S.String)),
+    tier: S.optional(S.NullOr(LitellmTypesRouterModelInfoTier)),
+    tiered_pricing: S.optional(
+      S.NullOr(LitellmTypesRouterModelInfoTieredPricingList),
+    ),
+    updated_at: S.optional(S.NullOr(S.String)),
+    updated_by: S.optional(S.NullOr(S.String)),
+  }),
+).annotate({
+  identifier: "LitellmTypesRouterModelInfo",
+}) as any as S.Schema<LitellmTypesRouterModelInfo>;
+
+export interface AddNewModelModelNewPostRequest {
+  litellm_params: LiteLLMParams;
+  model_info: LitellmTypesRouterModelInfo;
+  model_name: string;
+}
+export const AddNewModelModelNewPostRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    litellm_params: LiteLLMParams,
+    model_info: LitellmTypesRouterModelInfo,
+    model_name: S.String,
+  }).pipe(T.Http({ method: "POST", uri: "/model/new", code: 200 })),
+).annotate({
+  identifier: "AddNewModelModelNewPostRequest",
+}) as any as S.Schema<AddNewModelModelNewPostRequest>;
+
+export interface AddNewModelModelNewPostResponse {
+  body: unknown;
+}
+export const AddNewModelModelNewPostResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "AddNewModelModelNewPostResponse",
+}) as any as S.Schema<AddNewModelModelNewPostResponse>;
+
+export interface CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteRequest {}
+export const CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({
+        method: "DELETE",
+        uri: "/schedule/anthropic_beta_headers_reload",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteRequest",
+  }) as any as S.Schema<CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteRequest>;
+
+export interface CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteResponse {
+  body: unknown;
+}
+export const CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteResponse",
+  }) as any as S.Schema<CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteResponse>;
+
+export interface CancelModelCostMapReloadScheduleModelCostMapReloadDeleteRequest {}
+export const CancelModelCostMapReloadScheduleModelCostMapReloadDeleteRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({
+        method: "DELETE",
+        uri: "/schedule/model_cost_map_reload",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "CancelModelCostMapReloadScheduleModelCostMapReloadDeleteRequest",
+  }) as any as S.Schema<CancelModelCostMapReloadScheduleModelCostMapReloadDeleteRequest>;
+
+export interface CancelModelCostMapReloadScheduleModelCostMapReloadDeleteResponse {
+  body: unknown;
+}
+export const CancelModelCostMapReloadScheduleModelCostMapReloadDeleteResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "CancelModelCostMapReloadScheduleModelCostMapReloadDeleteResponse",
+  }) as any as S.Schema<CancelModelCostMapReloadScheduleModelCostMapReloadDeleteResponse>;
+
+export type CreateModelGroupAccessGroupNewPostRequestModelIdsList =
+  Array<string>;
+export const CreateModelGroupAccessGroupNewPostRequestModelIdsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<CreateModelGroupAccessGroupNewPostRequestModelIdsList>;
+
+export type CreateModelGroupAccessGroupNewPostRequestModelNamesList =
+  Array<string>;
+export const CreateModelGroupAccessGroupNewPostRequestModelNamesList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<CreateModelGroupAccessGroupNewPostRequestModelNamesList>;
+
+export interface CreateModelGroupAccessGroupNewPostRequest {
+  access_group: string;
+  model_ids?: CreateModelGroupAccessGroupNewPostRequestModelIdsList | null;
+  model_names?: CreateModelGroupAccessGroupNewPostRequestModelNamesList | null;
+}
+export const CreateModelGroupAccessGroupNewPostRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String,
+      model_ids: S.optional(
+        S.NullOr(CreateModelGroupAccessGroupNewPostRequestModelIdsList),
+      ),
+      model_names: S.optional(
+        S.NullOr(CreateModelGroupAccessGroupNewPostRequestModelNamesList),
+      ),
+    }).pipe(T.Http({ method: "POST", uri: "/access_group/new", code: 200 })),
+  ).annotate({
+    identifier: "CreateModelGroupAccessGroupNewPostRequest",
+  }) as any as S.Schema<CreateModelGroupAccessGroupNewPostRequest>;
+
+export type NewModelGroupResponseModelIdsList = Array<string>;
+export const NewModelGroupResponseModelIdsList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<NewModelGroupResponseModelIdsList>;
+
+export type NewModelGroupResponseModelNamesList = Array<string>;
+export const NewModelGroupResponseModelNamesList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<NewModelGroupResponseModelNamesList>;
+
+export interface NewModelGroupResponse {
+  access_group: string;
+  model_ids?: NewModelGroupResponseModelIdsList | null;
+  model_names?: NewModelGroupResponseModelNamesList | null;
+  models_updated: number;
+}
+export const NewModelGroupResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    access_group: S.String,
+    model_ids: S.optional(S.NullOr(NewModelGroupResponseModelIdsList)),
+    model_names: S.optional(S.NullOr(NewModelGroupResponseModelNamesList)),
+    models_updated: S.Number,
+  }),
+).annotate({
+  identifier: "NewModelGroupResponse",
+}) as any as S.Schema<NewModelGroupResponse>;
+
+export interface DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteRequest {
+  access_group: string;
+}
+export const DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String.pipe(T.Label()),
+    }).pipe(
+      T.Http({
+        method: "DELETE",
+        uri: "/access_group/{access_group}/delete",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteRequest",
+  }) as any as S.Schema<DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteRequest>;
+
+export interface DeleteModelGroupResponse {
+  access_group: string;
+  message: string;
+  models_updated: number;
+}
+export const DeleteModelGroupResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    access_group: S.String,
+    message: S.String,
+    models_updated: S.Number,
+  }),
+).annotate({
+  identifier: "DeleteModelGroupResponse",
+}) as any as S.Schema<DeleteModelGroupResponse>;
+
+export interface DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteRequest {
+  access_group: string;
+}
+export const DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String.pipe(T.Label()),
+    }).pipe(
+      T.Http({
+        method: "DELETE",
+        uri: "/access_group/{access_group}/budget",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteRequest",
+  }) as any as S.Schema<DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteRequest>;
+
+export interface DeleteAccessGroupBudgetResponse {
+  access_group: string;
+  budget_deleted: boolean;
+  message: string;
+}
+export const DeleteAccessGroupBudgetResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    access_group: S.String,
+    budget_deleted: S.Boolean,
+    message: S.String,
+  }),
+).annotate({
+  identifier: "DeleteAccessGroupBudgetResponse",
+}) as any as S.Schema<DeleteAccessGroupBudgetResponse>;
+
+export interface DeleteModelModelDeletePostRequest {
+  id: string;
+}
+export const DeleteModelModelDeletePostRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    id: S.String,
+  }).pipe(T.Http({ method: "POST", uri: "/model/delete", code: 200 })),
+).annotate({
+  identifier: "DeleteModelModelDeletePostRequest",
+}) as any as S.Schema<DeleteModelModelDeletePostRequest>;
+
+export interface DeleteModelModelDeletePostResponse {
+  body: unknown;
+}
+export const DeleteModelModelDeletePostResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "DeleteModelModelDeletePostResponse",
+}) as any as S.Schema<DeleteModelModelDeletePostResponse>;
+
+export interface GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetRequest {
+  access_group: string;
+}
+export const GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String.pipe(T.Label()),
+    }).pipe(
+      T.Http({
+        method: "GET",
+        uri: "/access_group/{access_group}/budget",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetRequest",
+  }) as any as S.Schema<GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetRequest>;
+
+export interface AccessGroupBudget {
+  budget_duration?: string | null;
+  budget_id: string;
+  budget_reset_at?: string | null;
+  max_budget?: number | null;
+  soft_budget?: number | null;
+}
+export const AccessGroupBudget = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    budget_duration: S.optional(S.NullOr(S.String)),
+    budget_id: S.String,
+    budget_reset_at: S.optional(S.NullOr(S.String)),
+    max_budget: S.optional(S.NullOr(S.Number)),
+    soft_budget: S.optional(S.NullOr(S.Number)),
+  }),
+).annotate({
+  identifier: "AccessGroupBudget",
+}) as any as S.Schema<AccessGroupBudget>;
+
+export interface AccessGroupBudgetResponse {
+  access_group: string;
+  budget?: AccessGroupBudget | null;
+  spend: number;
+}
+export const AccessGroupBudgetResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    access_group: S.String,
+    budget: S.optional(S.NullOr(AccessGroupBudget)),
+    spend: S.Number,
+  }),
+).annotate({
+  identifier: "AccessGroupBudgetResponse",
+}) as any as S.Schema<AccessGroupBudgetResponse>;
+
+export interface GetAccessGroupInfoAccessGroupAccessGroupInfoGetRequest {
+  access_group: string;
+}
+export const GetAccessGroupInfoAccessGroupAccessGroupInfoGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String.pipe(T.Label()),
+    }).pipe(
+      T.Http({
+        method: "GET",
+        uri: "/access_group/{access_group}/info",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "GetAccessGroupInfoAccessGroupAccessGroupInfoGetRequest",
+  }) as any as S.Schema<GetAccessGroupInfoAccessGroupAccessGroupInfoGetRequest>;
+
+export type AccessGroupInfoModelNamesList = Array<string>;
+export const AccessGroupInfoModelNamesList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<AccessGroupInfoModelNamesList>;
+
+export interface AccessGroupInfo {
+  access_group: string;
+  budget?: AccessGroupBudget | null;
+  deployment_count: number;
+  model_names: AccessGroupInfoModelNamesList;
+  spend?: number | null;
+}
+export const AccessGroupInfo = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    access_group: S.String,
+    budget: S.optional(S.NullOr(AccessGroupBudget)),
+    deployment_count: S.Number,
+    model_names: AccessGroupInfoModelNamesList,
+    spend: S.optional(S.NullOr(S.Number)),
+  }),
+).annotate({
+  identifier: "AccessGroupInfo",
+}) as any as S.Schema<AccessGroupInfo>;
+
+export interface GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetRequest {}
+export const GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({
+        method: "GET",
+        uri: "/schedule/anthropic_beta_headers_reload/status",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetRequest",
+  }) as any as S.Schema<GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetRequest>;
+
+export interface GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetResponse {
+  body: unknown;
+}
+export const GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetResponse",
+  }) as any as S.Schema<GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetResponse>;
+
+/** Which calibration examples, and for BUSINESS which tier criteria, the built-in classifier rubric carries. */
+export type ClassificationRubric = "legacy" | "agentic" | "chat" | "business";
+export const ClassificationRubric = S.String;
+
+export interface GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetRequest {
+  context_window_size?: number;
+  tier_labels?: string;
+  classification_rubric?: ClassificationRubric | (string & {});
+}
+export const GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      context_window_size: S.optional(S.Number.pipe(T.Query())),
+      tier_labels: S.optional(S.String.pipe(T.Query())),
+      classification_rubric: S.optional(ClassificationRubric.pipe(T.Query())),
+    }).pipe(
+      T.Http({
+        method: "GET",
+        uri: "/auto_router/classifier/default_prompt",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetRequest",
+  }) as any as S.Schema<GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetRequest>;
+
+/** The built-in system prompt an auto-router's LLM classifier uses when none is configured. Served so the dashboard's prompt editor prefills the rubric the proxy actually sends, rather than a copy in the frontend that drifts the moment the rubric is edited. */
+export interface AutoRouterClassifierDefaultPromptResponse {
+  system_prompt: string;
+}
+export const AutoRouterClassifierDefaultPromptResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      system_prompt: S.String,
+    }),
+  ).annotate({
+    identifier: "AutoRouterClassifierDefaultPromptResponse",
+  }) as any as S.Schema<AutoRouterClassifierDefaultPromptResponse>;
+
+export interface GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetRequest {}
+export const GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({
+        method: "GET",
+        uri: "/schedule/model_cost_map_reload/status",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetRequest",
+  }) as any as S.Schema<GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetRequest>;
+
+export interface GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetResponse {
+  body: unknown;
+}
+export const GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetResponse",
+  }) as any as S.Schema<GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetResponse>;
+
+export interface GetModelCostMapSourceModelCostMapSourceGetRequest {}
+export const GetModelCostMapSourceModelCostMapSourceGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({ method: "GET", uri: "/model/cost_map/source", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "GetModelCostMapSourceModelCostMapSourceGetRequest",
+  }) as any as S.Schema<GetModelCostMapSourceModelCostMapSourceGetRequest>;
+
+export interface GetModelCostMapSourceModelCostMapSourceGetResponse {
+  body: unknown;
+}
+export const GetModelCostMapSourceModelCostMapSourceGetResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "GetModelCostMapSourceModelCostMapSourceGetResponse",
+  }) as any as S.Schema<GetModelCostMapSourceModelCostMapSourceGetResponse>;
+
+export interface GetModelDeprecationsModelDeprecationRequest {
+  warn_within_days?: number;
+}
+export const GetModelDeprecationsModelDeprecationRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      warn_within_days: S.optional(S.Number.pipe(T.Query())),
+    }).pipe(T.Http({ method: "GET", uri: "/model/deprecations", code: 200 })),
+  ).annotate({
+    identifier: "GetModelDeprecationsModelDeprecationRequest",
+  }) as any as S.Schema<GetModelDeprecationsModelDeprecationRequest>;
+
+/** 'deprecated' if the date has passed, 'imminent' if it falls within warn_within_days, 'upcoming' otherwise. */
+export type ModelDeprecationInfoStatus = "upcoming" | "imminent" | "deprecated";
+export const ModelDeprecationInfoStatus = S.String;
+
+export interface ModelDeprecationInfo {
+  /** Days remaining until the deprecation date. Negative if the model is already deprecated. */
+  days_until_deprecation: number;
+  /** The date (UTC) when the model becomes deprecated. */
+  deprecation_date: string;
+  /** The underlying litellm model string the deprecation date is sourced from. */
+  litellm_model?: string | null;
+  /** The provider this model belongs to. */
+  litellm_provider?: string | null;
+  /** The public name of the model on the proxy (model_group). */
+  model_name: string;
+  /** 'deprecated' if the date has passed, 'imminent' if it falls within warn_within_days, 'upcoming' otherwise. */
+  status: ModelDeprecationInfoStatus;
+}
+export const ModelDeprecationInfo = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    days_until_deprecation: S.Number,
+    deprecation_date: S.String,
+    litellm_model: S.optional(S.NullOr(S.String)),
+    litellm_provider: S.optional(S.NullOr(S.String)),
+    model_name: S.String,
+    status: ModelDeprecationInfoStatus,
+  }),
+).annotate({
+  identifier: "ModelDeprecationInfo",
+}) as any as S.Schema<ModelDeprecationInfo>;
+
+/** Models whose deprecation date has already passed. */
+export type ModelDeprecationResponseDeprecatedList =
+  Array<ModelDeprecationInfo>;
+export const ModelDeprecationResponseDeprecatedList = /*@__PURE__*/ S.Array(
+  ModelDeprecationInfo,
+) as any as S.Schema<ModelDeprecationResponseDeprecatedList>;
+
+/** Models whose deprecation date is within warn_within_days from today and require immediate migration planning. */
+export type ModelDeprecationResponseImminentList = Array<ModelDeprecationInfo>;
+export const ModelDeprecationResponseImminentList = /*@__PURE__*/ S.Array(
+  ModelDeprecationInfo,
+) as any as S.Schema<ModelDeprecationResponseImminentList>;
+
+/** Models with a future deprecation date outside the warn window. */
+export type ModelDeprecationResponseUpcomingList = Array<ModelDeprecationInfo>;
+export const ModelDeprecationResponseUpcomingList = /*@__PURE__*/ S.Array(
+  ModelDeprecationInfo,
+) as any as S.Schema<ModelDeprecationResponseUpcomingList>;
+
+export interface ModelDeprecationResponse {
+  /** UTC timestamp when the deprecation snapshot was generated. */
+  checked_at: string;
+  /** Models whose deprecation date has already passed. */
+  deprecated?: ModelDeprecationResponseDeprecatedList;
+  /** Models whose deprecation date is within warn_within_days from today and require immediate migration planning. */
+  imminent?: ModelDeprecationResponseImminentList;
+  /** Models with a future deprecation date outside the warn window. */
+  upcoming?: ModelDeprecationResponseUpcomingList;
+  /** The window (in days) used to bucket 'imminent' models. */
+  warn_within_days: number;
+}
+export const ModelDeprecationResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    checked_at: S.String,
+    deprecated: S.optional(ModelDeprecationResponseDeprecatedList),
+    imminent: S.optional(ModelDeprecationResponseImminentList),
+    upcoming: S.optional(ModelDeprecationResponseUpcomingList),
+    warn_within_days: S.Number,
+  }),
+).annotate({
+  identifier: "ModelDeprecationResponse",
+}) as any as S.Schema<ModelDeprecationResponse>;
+
+export interface GetModelDeprecationsV1ModelDeprecationRequest {
+  warn_within_days?: number;
+}
+export const GetModelDeprecationsV1ModelDeprecationRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      warn_within_days: S.optional(S.Number.pipe(T.Query())),
+    }).pipe(
+      T.Http({ method: "GET", uri: "/v1/model/deprecations", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "GetModelDeprecationsV1ModelDeprecationRequest",
+  }) as any as S.Schema<GetModelDeprecationsV1ModelDeprecationRequest>;
+
+export interface GetModelGroupInfoModelGroupInfoRequest {
+  model_group?: string;
+}
+export const GetModelGroupInfoModelGroupInfoRequest = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      model_group: S.optional(S.String.pipe(T.Query())),
+    }).pipe(T.Http({ method: "GET", uri: "/model_group/info", code: 200 })),
+).annotate({
+  identifier: "GetModelGroupInfoModelGroupInfoRequest",
+}) as any as S.Schema<GetModelGroupInfoModelGroupInfoRequest>;
+
+export interface GetModelGroupInfoModelGroupInfoResponse {
+  body: unknown;
+}
+export const GetModelGroupInfoModelGroupInfoResponse = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+).annotate({
+  identifier: "GetModelGroupInfoModelGroupInfoResponse",
+}) as any as S.Schema<GetModelGroupInfoModelGroupInfoResponse>;
+
+export interface GetModelInfoModelsModelIdRequest {
+  model_id: string;
+  team_id?: string;
+  healthy_only?: boolean;
+}
+export const GetModelInfoModelsModelIdRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    model_id: S.String.pipe(T.Label()),
+    team_id: S.optional(S.String.pipe(T.Query())),
+    healthy_only: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/models/{model_id}", code: 200 })),
+).annotate({
+  identifier: "GetModelInfoModelsModelIdRequest",
+}) as any as S.Schema<GetModelInfoModelsModelIdRequest>;
+
+export interface GetModelInfoModelsModelIdResponse {
+  body: unknown;
+}
+export const GetModelInfoModelsModelIdResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "GetModelInfoModelsModelIdResponse",
+}) as any as S.Schema<GetModelInfoModelsModelIdResponse>;
+
+export interface GetModelInfoV1ModelInfoRequest {
+  litellm_model_id?: string;
+  /** When true, filter to deployments the caller can use via direct access or team membership. */
+  include_team_models?: boolean;
+  /** Filter models by team ID. Returns models with direct_access=True or teamId in access_via_team_ids */
+  teamId?: string;
+  healthy_only?: boolean;
+}
+export const GetModelInfoV1ModelInfoRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    litellm_model_id: S.optional(S.String.pipe(T.Query())),
+    include_team_models: S.optional(S.Boolean.pipe(T.Query())),
+    teamId: S.optional(S.String.pipe(T.Query())),
+    healthy_only: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/model/info", code: 200 })),
+).annotate({
+  identifier: "GetModelInfoV1ModelInfoRequest",
+}) as any as S.Schema<GetModelInfoV1ModelInfoRequest>;
+
+export interface GetModelInfoV1ModelInfoResponse {
+  body: unknown;
+}
+export const GetModelInfoV1ModelInfoResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "GetModelInfoV1ModelInfoResponse",
+}) as any as S.Schema<GetModelInfoV1ModelInfoResponse>;
+
+export interface GetModelInfoV1ModelsModelIdRequest {
+  model_id: string;
+  team_id?: string;
+  healthy_only?: boolean;
+}
+export const GetModelInfoV1ModelsModelIdRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    model_id: S.String.pipe(T.Label()),
+    team_id: S.optional(S.String.pipe(T.Query())),
+    healthy_only: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/v1/models/{model_id}", code: 200 })),
+).annotate({
+  identifier: "GetModelInfoV1ModelsModelIdRequest",
+}) as any as S.Schema<GetModelInfoV1ModelsModelIdRequest>;
+
+export interface GetModelInfoV1ModelsModelIdResponse {
+  body: unknown;
+}
+export const GetModelInfoV1ModelsModelIdResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "GetModelInfoV1ModelsModelIdResponse",
+}) as any as S.Schema<GetModelInfoV1ModelsModelIdResponse>;
+
+export interface GetModelInfoV1V1ModelInfoRequest {
+  litellm_model_id?: string;
+  /** When true, filter to deployments the caller can use via direct access or team membership. */
+  include_team_models?: boolean;
+  /** Filter models by team ID. Returns models with direct_access=True or teamId in access_via_team_ids */
+  teamId?: string;
+  healthy_only?: boolean;
+}
+export const GetModelInfoV1V1ModelInfoRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    litellm_model_id: S.optional(S.String.pipe(T.Query())),
+    include_team_models: S.optional(S.Boolean.pipe(T.Query())),
+    teamId: S.optional(S.String.pipe(T.Query())),
+    healthy_only: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/v1/model/info", code: 200 })),
+).annotate({
+  identifier: "GetModelInfoV1V1ModelInfoRequest",
+}) as any as S.Schema<GetModelInfoV1V1ModelInfoRequest>;
+
+export interface GetModelInfoV1V1ModelInfoResponse {
+  body: unknown;
+}
+export const GetModelInfoV1V1ModelInfoResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "GetModelInfoV1V1ModelInfoResponse",
+}) as any as S.Schema<GetModelInfoV1V1ModelInfoResponse>;
+
+export interface GetModelInfoV2V2ModelInfoRequest {
+  /** Specify the model name (optional) */
+  model?: string;
+  /** Only return models added by this user */
+  user_models_only?: boolean;
+  /** Return all models across all teams user is in. */
+  include_team_models?: boolean;
+  debug?: boolean;
+  /** Page number */
+  page?: number;
+  /** Page size */
+  size?: number;
+  /** Search model names (case-insensitive partial match) */
+  search?: string;
+  /** Search for a specific model by its unique ID */
+  modelId?: string;
+  /** Filter models by team ID. Returns models with direct_access=True or teamId in access_via_team_ids */
+  teamId?: string;
+  /** Field to sort by. Options: model_name, created_at, updated_at, costs, status */
+  sortBy?: string;
+  /** Sort order. Options: asc, desc */
+  sortOrder?: string;
+  /** Omit auto-router deployments (litellm model prefixed `auto_router/`). They select among deployments rather than being deployments themselves, so a caller rendering a deployment list can leave them out. Defaults to false, so existing callers are unaffected */
+  exclude_auto_routers?: boolean;
+}
+export const GetModelInfoV2V2ModelInfoRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    model: S.optional(S.String.pipe(T.Query())),
+    user_models_only: S.optional(S.Boolean.pipe(T.Query())),
+    include_team_models: S.optional(S.Boolean.pipe(T.Query())),
+    debug: S.optional(S.Boolean.pipe(T.Query())),
+    page: S.optional(S.Number.pipe(T.Query())),
+    size: S.optional(S.Number.pipe(T.Query())),
+    search: S.optional(S.String.pipe(T.Query())),
+    modelId: S.optional(S.String.pipe(T.Query())),
+    teamId: S.optional(S.String.pipe(T.Query())),
+    sortBy: S.optional(S.String.pipe(T.Query())),
+    sortOrder: S.optional(S.String.pipe(T.Query())),
+    exclude_auto_routers: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/v2/model/info", code: 200 })),
+).annotate({
+  identifier: "GetModelInfoV2V2ModelInfoRequest",
+}) as any as S.Schema<GetModelInfoV2V2ModelInfoRequest>;
+
+export interface GetModelInfoV2V2ModelInfoResponse {
+  body: unknown;
+}
+export const GetModelInfoV2V2ModelInfoResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "GetModelInfoV2V2ModelInfoResponse",
+}) as any as S.Schema<GetModelInfoV2V2ModelInfoResponse>;
+
+export interface GetModelMetricsExceptionsModelMetricsExceptionRequest {
+  _selected_model_group?: string;
+  startTime?: string;
+  endTime?: string;
+  api_key?: string;
+  customer?: string;
+}
+export const GetModelMetricsExceptionsModelMetricsExceptionRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      _selected_model_group: S.optional(S.String.pipe(T.Query())),
+      startTime: S.optional(S.String.pipe(T.Query())),
+      endTime: S.optional(S.String.pipe(T.Query())),
+      api_key: S.optional(S.String.pipe(T.Query())),
+      customer: S.optional(S.String.pipe(T.Query())),
+    }).pipe(
+      T.Http({ method: "GET", uri: "/model/metrics/exceptions", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "GetModelMetricsExceptionsModelMetricsExceptionRequest",
+  }) as any as S.Schema<GetModelMetricsExceptionsModelMetricsExceptionRequest>;
+
+export interface GetModelMetricsExceptionsModelMetricsExceptionResponse {
+  body: unknown;
+}
+export const GetModelMetricsExceptionsModelMetricsExceptionResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "GetModelMetricsExceptionsModelMetricsExceptionResponse",
+  }) as any as S.Schema<GetModelMetricsExceptionsModelMetricsExceptionResponse>;
+
+export interface GetModelMetricsModelMetricsRequest {
+  _selected_model_group?: string;
+  startTime?: string;
+  endTime?: string;
+  api_key?: string;
+  customer?: string;
+}
+export const GetModelMetricsModelMetricsRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    _selected_model_group: S.optional(S.String.pipe(T.Query())),
+    startTime: S.optional(S.String.pipe(T.Query())),
+    endTime: S.optional(S.String.pipe(T.Query())),
+    api_key: S.optional(S.String.pipe(T.Query())),
+    customer: S.optional(S.String.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/model/metrics", code: 200 })),
+).annotate({
+  identifier: "GetModelMetricsModelMetricsRequest",
+}) as any as S.Schema<GetModelMetricsModelMetricsRequest>;
+
+export interface GetModelMetricsModelMetricsResponse {
+  body: unknown;
+}
+export const GetModelMetricsModelMetricsResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "GetModelMetricsModelMetricsResponse",
+}) as any as S.Schema<GetModelMetricsModelMetricsResponse>;
+
+export interface GetModelMetricsSlowResponsesModelMetricsSlowResponseRequest {
+  _selected_model_group?: string;
+  startTime?: string;
+  endTime?: string;
+  api_key?: string;
+  customer?: string;
+}
+export const GetModelMetricsSlowResponsesModelMetricsSlowResponseRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      _selected_model_group: S.optional(S.String.pipe(T.Query())),
+      startTime: S.optional(S.String.pipe(T.Query())),
+      endTime: S.optional(S.String.pipe(T.Query())),
+      api_key: S.optional(S.String.pipe(T.Query())),
+      customer: S.optional(S.String.pipe(T.Query())),
+    }).pipe(
+      T.Http({
+        method: "GET",
+        uri: "/model/metrics/slow_responses",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "GetModelMetricsSlowResponsesModelMetricsSlowResponseRequest",
+  }) as any as S.Schema<GetModelMetricsSlowResponsesModelMetricsSlowResponseRequest>;
+
+export interface GetModelMetricsSlowResponsesModelMetricsSlowResponseResponse {
+  body: unknown;
+}
+export const GetModelMetricsSlowResponsesModelMetricsSlowResponseResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "GetModelMetricsSlowResponsesModelMetricsSlowResponseResponse",
+  }) as any as S.Schema<GetModelMetricsSlowResponsesModelMetricsSlowResponseResponse>;
+
+export interface GetModelSettingsModelSettingsRequest {}
+export const GetModelSettingsModelSettingsRequest = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({}).pipe(
+      T.Http({ method: "GET", uri: "/model/settings", code: 200 }),
+    ),
+).annotate({
+  identifier: "GetModelSettingsModelSettingsRequest",
+}) as any as S.Schema<GetModelSettingsModelSettingsRequest>;
+
+export interface GetModelSettingsModelSettingsResponse {
+  body: unknown;
+}
+export const GetModelSettingsModelSettingsResponse = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+).annotate({
+  identifier: "GetModelSettingsModelSettingsResponse",
+}) as any as S.Schema<GetModelSettingsModelSettingsResponse>;
+
+export interface GetModelStreamingMetricsModelStreamingMetricsRequest {
+  _selected_model_group?: string;
+  startTime?: string;
+  endTime?: string;
+}
+export const GetModelStreamingMetricsModelStreamingMetricsRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      _selected_model_group: S.optional(S.String.pipe(T.Query())),
+      startTime: S.optional(S.String.pipe(T.Query())),
+      endTime: S.optional(S.String.pipe(T.Query())),
+    }).pipe(
+      T.Http({ method: "GET", uri: "/model/streaming_metrics", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "GetModelStreamingMetricsModelStreamingMetricsRequest",
+  }) as any as S.Schema<GetModelStreamingMetricsModelStreamingMetricsRequest>;
+
+export interface GetModelStreamingMetricsModelStreamingMetricsResponse {
+  body: unknown;
+}
+export const GetModelStreamingMetricsModelStreamingMetricsResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "GetModelStreamingMetricsModelStreamingMetricsResponse",
+  }) as any as S.Schema<GetModelStreamingMetricsModelStreamingMetricsResponse>;
+
+export interface ListAccessGroupsAccessGroupListGetRequest {}
+export const ListAccessGroupsAccessGroupListGetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({ method: "GET", uri: "/access_group/list", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "ListAccessGroupsAccessGroupListGetRequest",
+  }) as any as S.Schema<ListAccessGroupsAccessGroupListGetRequest>;
+
+export type ListAccessGroupsResponseAccessGroupsList = Array<AccessGroupInfo>;
+export const ListAccessGroupsResponseAccessGroupsList = /*@__PURE__*/ S.Array(
+  AccessGroupInfo,
+) as any as S.Schema<ListAccessGroupsResponseAccessGroupsList>;
+
+export interface ListAccessGroupsResponse {
+  access_groups: ListAccessGroupsResponseAccessGroupsList;
+}
+export const ListAccessGroupsResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    access_groups: ListAccessGroupsResponseAccessGroupsList,
+  }),
+).annotate({
+  identifier: "ListAccessGroupsResponse",
+}) as any as S.Schema<ListAccessGroupsResponse>;
+
+export interface ModelListModelsGetRequest {
+  return_wildcard_routes?: boolean;
+  team_id?: string;
+  include_model_access_groups?: boolean;
+  only_model_access_groups?: boolean;
+  include_metadata?: boolean;
+  fallback_type?: string;
+  scope?: string;
+  healthy_only?: boolean;
+}
+export const ModelListModelsGetRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    return_wildcard_routes: S.optional(S.Boolean.pipe(T.Query())),
+    team_id: S.optional(S.String.pipe(T.Query())),
+    include_model_access_groups: S.optional(S.Boolean.pipe(T.Query())),
+    only_model_access_groups: S.optional(S.Boolean.pipe(T.Query())),
+    include_metadata: S.optional(S.Boolean.pipe(T.Query())),
+    fallback_type: S.optional(S.String.pipe(T.Query())),
+    scope: S.optional(S.String.pipe(T.Query())),
+    healthy_only: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/models", code: 200 })),
+).annotate({
+  identifier: "ModelListModelsGetRequest",
+}) as any as S.Schema<ModelListModelsGetRequest>;
+
+export interface ModelListModelsGetResponse {
+  body: unknown;
+}
+export const ModelListModelsGetResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "ModelListModelsGetResponse",
+}) as any as S.Schema<ModelListModelsGetResponse>;
+
+export interface ModelListV1ModelsGetRequest {
+  return_wildcard_routes?: boolean;
+  team_id?: string;
+  include_model_access_groups?: boolean;
+  only_model_access_groups?: boolean;
+  include_metadata?: boolean;
+  fallback_type?: string;
+  scope?: string;
+  healthy_only?: boolean;
+}
+export const ModelListV1ModelsGetRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    return_wildcard_routes: S.optional(S.Boolean.pipe(T.Query())),
+    team_id: S.optional(S.String.pipe(T.Query())),
+    include_model_access_groups: S.optional(S.Boolean.pipe(T.Query())),
+    only_model_access_groups: S.optional(S.Boolean.pipe(T.Query())),
+    include_metadata: S.optional(S.Boolean.pipe(T.Query())),
+    fallback_type: S.optional(S.String.pipe(T.Query())),
+    scope: S.optional(S.String.pipe(T.Query())),
+    healthy_only: S.optional(S.Boolean.pipe(T.Query())),
+  }).pipe(T.Http({ method: "GET", uri: "/v1/models", code: 200 })),
+).annotate({
+  identifier: "ModelListV1ModelsGetRequest",
+}) as any as S.Schema<ModelListV1ModelsGetRequest>;
+
+export interface ModelListV1ModelsGetResponse {
+  body: unknown;
+}
+export const ModelListV1ModelsGetResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "ModelListV1ModelsGetResponse",
+}) as any as S.Schema<ModelListV1ModelsGetResponse>;
+
+export type UpdateLiteLLMParamsAdaptiveRouterConfigMap = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsAdaptiveRouterConfigMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<UpdateLiteLLMParamsAdaptiveRouterConfigMap>;
+
+export type UpdateLiteLLMParamsBedrockTagsList = Array<unknown>;
+export const UpdateLiteLLMParamsBedrockTagsList = /*@__PURE__*/ S.Array(
+  S.Unknown,
+) as any as S.Schema<UpdateLiteLLMParamsBedrockTagsList>;
+
+export type UpdateLiteLLMParamsComplexityRouterConfigMap = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsComplexityRouterConfigMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<UpdateLiteLLMParamsComplexityRouterConfigMap>;
+
+export type UpdateLiteLLMParamsConfigurableClientsideAuthParamsItem =
+  | string
+  | ConfigurableClientsideParamsCustomAuthInput;
+export const UpdateLiteLLMParamsConfigurableClientsideAuthParamsItem =
+  S.Unknown as any as S.Schema<UpdateLiteLLMParamsConfigurableClientsideAuthParamsItem>;
+
+export type UpdateLiteLLMParamsConfigurableClientsideAuthParamsList =
+  Array<UpdateLiteLLMParamsConfigurableClientsideAuthParamsItem>;
+export const UpdateLiteLLMParamsConfigurableClientsideAuthParamsList =
+  /*@__PURE__*/ S.Array(
+    UpdateLiteLLMParamsConfigurableClientsideAuthParamsItem,
+  ) as any as S.Schema<UpdateLiteLLMParamsConfigurableClientsideAuthParamsList>;
+
+export type UpdateLiteLLMParamsMilvusPartitionNamesList = Array<string>;
+export const UpdateLiteLLMParamsMilvusPartitionNamesList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<UpdateLiteLLMParamsMilvusPartitionNamesList>;
+
+export type UpdateLiteLLMParamsMockResponse = string | ModelResponse | unknown;
+export const UpdateLiteLLMParamsMockResponse =
+  S.Unknown as any as S.Schema<UpdateLiteLLMParamsMockResponse>;
+
+export type UpdateLiteLLMParamsModelInfoMap = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsModelInfoMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<UpdateLiteLLMParamsModelInfoMap>;
+
+export type UpdateLiteLLMParamsQualityRouterConfigMap = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsQualityRouterConfigMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<UpdateLiteLLMParamsQualityRouterConfigMap>;
+
+export type UpdateLiteLLMParamsSearchContextCostPerQueryMap = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsSearchContextCostPerQueryMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<UpdateLiteLLMParamsSearchContextCostPerQueryMap>;
+
+export type UpdateLiteLLMParamsStreamTimeout = number | string;
+export const UpdateLiteLLMParamsStreamTimeout =
+  S.Unknown as any as S.Schema<UpdateLiteLLMParamsStreamTimeout>;
+
+export type UpdateLiteLLMParamsTagRegexList = Array<string>;
+export const UpdateLiteLLMParamsTagRegexList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<UpdateLiteLLMParamsTagRegexList>;
+
+export type UpdateLiteLLMParamsTagsList = Array<string>;
+export const UpdateLiteLLMParamsTagsList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<UpdateLiteLLMParamsTagsList>;
+
+export type UpdateLiteLLMParamsTieredPricingItemMap = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsTieredPricingItemMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<UpdateLiteLLMParamsTieredPricingItemMap>;
+
+export type UpdateLiteLLMParamsTieredPricingList =
+  Array<UpdateLiteLLMParamsTieredPricingItemMap>;
+export const UpdateLiteLLMParamsTieredPricingList = /*@__PURE__*/ S.Array(
+  UpdateLiteLLMParamsTieredPricingItemMap,
+) as any as S.Schema<UpdateLiteLLMParamsTieredPricingList>;
+
+export type UpdateLiteLLMParamsTimeout = number | string;
+export const UpdateLiteLLMParamsTimeout =
+  S.Unknown as any as S.Schema<UpdateLiteLLMParamsTimeout>;
+
+export type UpdateLiteLLMParamsVertexCredentialsCase1Map = {
+  [key: string]: unknown | undefined;
+};
+export const UpdateLiteLLMParamsVertexCredentialsCase1Map =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<UpdateLiteLLMParamsVertexCredentialsCase1Map>;
+
+export type UpdateLiteLLMParamsVertexCredentials =
+  | string
+  | UpdateLiteLLMParamsVertexCredentialsCase1Map;
+export const UpdateLiteLLMParamsVertexCredentials =
+  S.Unknown as any as S.Schema<UpdateLiteLLMParamsVertexCredentials>;
+
+export interface UpdateLiteLLMParams {
+  adaptive_router_config?: UpdateLiteLLMParamsAdaptiveRouterConfigMap | null;
+  adaptive_router_default_model?: string | null;
+  allow_client_keepalive_override?: boolean | null;
+  annotation_cost_per_page?: number | null;
+  api_base?: string | null;
+  api_key?: string | null;
+  api_version?: string | null;
+  auto_router_config?: string | null;
+  auto_router_config_path?: string | null;
+  auto_router_default_model?: string | null;
+  auto_router_embedding_model?: string | null;
+  auto_router_max_input_chars?: number | null;
+  aws_access_key_id?: string | null;
+  aws_batch_role_arn?: string | null;
+  aws_bedrock_project_id?: string | null;
+  aws_bedrock_runtime_endpoint?: string | null;
+  aws_external_id?: string | null;
+  aws_profile_name?: string | null;
+  aws_region_name?: string | null;
+  aws_role_name?: string | null;
+  aws_secret_access_key?: string | null;
+  aws_session_name?: string | null;
+  aws_session_token?: string | null;
+  aws_sts_endpoint?: string | null;
+  aws_web_identity_token?: string | null;
+  azure_ad_token?: string | null;
+  bedrock_tags?: UpdateLiteLLMParamsBedrockTagsList | null;
+  budget_duration?: string | null;
+  cache_creation_input_audio_token_cost?: number | null;
+  cache_creation_input_token_cost?: number | null;
+  cache_creation_input_token_cost_above_1hr?: number | null;
+  cache_creation_input_token_cost_above_200k_tokens?: number | null;
+  cache_creation_input_token_cost_above_272k_tokens?: number | null;
+  cache_creation_input_token_cost_above_272k_tokens_flex?: number | null;
+  cache_creation_input_token_cost_above_272k_tokens_priority?: number | null;
+  cache_creation_input_token_cost_flex?: number | null;
+  cache_creation_input_token_cost_priority?: number | null;
+  cache_creation_input_token_cost_ultrafast?: number | null;
+  cache_read_input_audio_token_cost?: number | null;
+  cache_read_input_token_cost?: number | null;
+  cache_read_input_token_cost_above_200k_tokens?: number | null;
+  cache_read_input_token_cost_above_200k_tokens_priority?: number | null;
+  cache_read_input_token_cost_above_272k_tokens?: number | null;
+  cache_read_input_token_cost_above_272k_tokens_flex?: number | null;
+  cache_read_input_token_cost_above_272k_tokens_priority?: number | null;
+  cache_read_input_token_cost_above_512k_tokens?: number | null;
+  cache_read_input_token_cost_flex?: number | null;
+  cache_read_input_token_cost_priority?: number | null;
+  cache_read_input_token_cost_ultrafast?: number | null;
+  citation_cost_per_token?: number | null;
+  complexity_router_config?: UpdateLiteLLMParamsComplexityRouterConfigMap | null;
+  complexity_router_default_model?: string | null;
+  configurable_clientside_auth_params?: UpdateLiteLLMParamsConfigurableClientsideAuthParamsList | null;
+  custom_llm_provider?: string | null;
+  default_api_key_rpm_limit?: number | null;
+  default_api_key_tpm_limit?: number | null;
+  gcs_bucket_name?: string | null;
+  google_maps_grounding_cost_per_query?: number | null;
+  input_cost_per_audio_per_second?: number | null;
+  input_cost_per_audio_per_second_above_128k_tokens?: number | null;
+  input_cost_per_audio_token?: number | null;
+  input_cost_per_character?: number | null;
+  input_cost_per_character_above_128k_tokens?: number | null;
+  input_cost_per_image?: number | null;
+  input_cost_per_image_above_128k_tokens?: number | null;
+  input_cost_per_image_token?: number | null;
+  input_cost_per_pixel?: number | null;
+  input_cost_per_query?: number | null;
+  input_cost_per_second?: number | null;
+  input_cost_per_token?: number | null;
+  input_cost_per_token_above_128k_tokens?: number | null;
+  input_cost_per_token_above_200k_tokens?: number | null;
+  input_cost_per_token_above_200k_tokens_priority?: number | null;
+  input_cost_per_token_above_272k_tokens?: number | null;
+  input_cost_per_token_above_272k_tokens_flex?: number | null;
+  input_cost_per_token_above_272k_tokens_priority?: number | null;
+  input_cost_per_token_above_512k_tokens?: number | null;
+  input_cost_per_token_batches?: number | null;
+  input_cost_per_token_cache_hit?: number | null;
+  input_cost_per_token_flex?: number | null;
+  input_cost_per_token_priority?: number | null;
+  input_cost_per_token_ultrafast?: number | null;
+  input_cost_per_video_per_second?: number | null;
+  input_cost_per_video_per_second_above_128k_tokens?: number | null;
+  input_cost_per_video_per_second_above_15s_interval?: number | null;
+  input_cost_per_video_per_second_above_8s_interval?: number | null;
+  input_cost_per_video_token?: number | null;
+  itpm?: number | null;
+  keepalive_seconds?: number | null;
+  litellm_credential_name?: string | null;
+  litellm_trace_id?: string | null;
+  max_budget?: number | null;
+  max_file_size_mb?: number | null;
+  max_retries?: number | null;
+  merge_reasoning_content_in_choices?: boolean | null;
+  milvus_db_name?: string | null;
+  milvus_partition_names?: UpdateLiteLLMParamsMilvusPartitionNamesList | null;
+  milvus_text_field?: string | null;
+  mock_response?: UpdateLiteLLMParamsMockResponse | null;
+  model?: string | null;
+  model_info?: UpdateLiteLLMParamsModelInfoMap | null;
+  ocr_cost_per_credit?: number | null;
+  ocr_cost_per_page?: number | null;
+  organization?: string | null;
+  otpm?: number | null;
+  output_cost_per_audio_per_second?: number | null;
+  output_cost_per_audio_token?: number | null;
+  output_cost_per_character?: number | null;
+  output_cost_per_character_above_128k_tokens?: number | null;
+  output_cost_per_image?: number | null;
+  output_cost_per_image_token?: number | null;
+  output_cost_per_pixel?: number | null;
+  output_cost_per_reasoning_token?: number | null;
+  output_cost_per_reasoning_token_flex?: number | null;
+  output_cost_per_reasoning_token_priority?: number | null;
+  output_cost_per_second?: number | null;
+  output_cost_per_second_1080p?: number | null;
+  output_cost_per_second_480p?: number | null;
+  output_cost_per_second_4k?: number | null;
+  output_cost_per_token?: number | null;
+  output_cost_per_token_above_128k_tokens?: number | null;
+  output_cost_per_token_above_200k_tokens?: number | null;
+  output_cost_per_token_above_200k_tokens_priority?: number | null;
+  output_cost_per_token_above_272k_tokens?: number | null;
+  output_cost_per_token_above_272k_tokens_flex?: number | null;
+  output_cost_per_token_above_272k_tokens_priority?: number | null;
+  output_cost_per_token_above_512k_tokens?: number | null;
+  output_cost_per_token_batches?: number | null;
+  output_cost_per_token_flex?: number | null;
+  output_cost_per_token_priority?: number | null;
+  output_cost_per_token_ultrafast?: number | null;
+  output_cost_per_video_per_second?: number | null;
+  output_cost_per_video_token?: number | null;
+  output_vector_size?: number | null;
+  quality_router_config?: UpdateLiteLLMParamsQualityRouterConfigMap | null;
+  quality_router_default_model?: string | null;
+  region_name?: string | null;
+  regional_endpoint_uplift_multiplier?: number | null;
+  regional_processing_uplift_multiplier_eu?: number | null;
+  regional_processing_uplift_multiplier_us?: number | null;
+  rpm?: number | null;
+  s3_bucket_name?: string | null;
+  s3_encryption_key_id?: string | null;
+  s3_output_bucket_name?: string | null;
+  s3_region_name?: string | null;
+  search_context_cost_per_query?: UpdateLiteLLMParamsSearchContextCostPerQueryMap | null;
+  stream_timeout?: UpdateLiteLLMParamsStreamTimeout | null;
+  tag_regex?: UpdateLiteLLMParamsTagRegexList | null;
+  tags?: UpdateLiteLLMParamsTagsList | null;
+  tiered_pricing?: UpdateLiteLLMParamsTieredPricingList | null;
+  timeout?: UpdateLiteLLMParamsTimeout | null;
+  tpm?: number | null;
+  use_chat_completions_api?: boolean | null;
+  use_in_pass_through?: boolean | null;
+  use_litellm_proxy?: boolean | null;
+  /** Use stored xAI OAuth credentials when no xAI API key is configured. */
+  use_xai_oauth?: boolean | null;
+  valkey_embedding_field?: string | null;
+  valkey_host?: string | null;
+  valkey_password?: string | null;
+  valkey_port?: number | null;
+  valkey_ssl?: boolean | null;
+  valkey_text_field?: string | null;
+  vector_store_id?: string | null;
+  vertex_credentials?: UpdateLiteLLMParamsVertexCredentials | null;
+  vertex_location?: string | null;
+  vertex_project?: string | null;
+  watsonx_region_name?: string | null;
+}
+export const UpdateLiteLLMParams = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    adaptive_router_config: S.optional(
+      S.NullOr(UpdateLiteLLMParamsAdaptiveRouterConfigMap),
+    ),
+    adaptive_router_default_model: S.optional(S.NullOr(S.String)),
+    allow_client_keepalive_override: S.optional(S.NullOr(S.Boolean)),
+    annotation_cost_per_page: S.optional(S.NullOr(S.Number)),
+    api_base: S.optional(S.NullOr(S.String)),
+    api_key: S.optional(S.NullOr(S.String)),
+    api_version: S.optional(S.NullOr(S.String)),
+    auto_router_config: S.optional(S.NullOr(S.String)),
+    auto_router_config_path: S.optional(S.NullOr(S.String)),
+    auto_router_default_model: S.optional(S.NullOr(S.String)),
+    auto_router_embedding_model: S.optional(S.NullOr(S.String)),
+    auto_router_max_input_chars: S.optional(S.NullOr(S.Number)),
+    aws_access_key_id: S.optional(S.NullOr(S.String)),
+    aws_batch_role_arn: S.optional(S.NullOr(S.String)),
+    aws_bedrock_project_id: S.optional(S.NullOr(S.String)),
+    aws_bedrock_runtime_endpoint: S.optional(S.NullOr(S.String)),
+    aws_external_id: S.optional(S.NullOr(S.String)),
+    aws_profile_name: S.optional(S.NullOr(S.String)),
+    aws_region_name: S.optional(S.NullOr(S.String)),
+    aws_role_name: S.optional(S.NullOr(S.String)),
+    aws_secret_access_key: S.optional(S.NullOr(S.String)),
+    aws_session_name: S.optional(S.NullOr(S.String)),
+    aws_session_token: S.optional(S.NullOr(S.String)),
+    aws_sts_endpoint: S.optional(S.NullOr(S.String)),
+    aws_web_identity_token: S.optional(S.NullOr(S.String)),
+    azure_ad_token: S.optional(S.NullOr(S.String)),
+    bedrock_tags: S.optional(S.NullOr(UpdateLiteLLMParamsBedrockTagsList)),
+    budget_duration: S.optional(S.NullOr(S.String)),
+    cache_creation_input_audio_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_above_1hr: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_above_200k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_above_272k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_above_272k_tokens_flex: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_creation_input_token_cost_flex: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_priority: S.optional(S.NullOr(S.Number)),
+    cache_creation_input_token_cost_ultrafast: S.optional(S.NullOr(S.Number)),
+    cache_read_input_audio_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost_above_200k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_200k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_272k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_272k_tokens_flex: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_above_512k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    cache_read_input_token_cost_flex: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost_priority: S.optional(S.NullOr(S.Number)),
+    cache_read_input_token_cost_ultrafast: S.optional(S.NullOr(S.Number)),
+    citation_cost_per_token: S.optional(S.NullOr(S.Number)),
+    complexity_router_config: S.optional(
+      S.NullOr(UpdateLiteLLMParamsComplexityRouterConfigMap),
+    ),
+    complexity_router_default_model: S.optional(S.NullOr(S.String)),
+    configurable_clientside_auth_params: S.optional(
+      S.NullOr(UpdateLiteLLMParamsConfigurableClientsideAuthParamsList),
+    ),
+    custom_llm_provider: S.optional(S.NullOr(S.String)),
+    default_api_key_rpm_limit: S.optional(S.NullOr(S.Number)),
+    default_api_key_tpm_limit: S.optional(S.NullOr(S.Number)),
+    gcs_bucket_name: S.optional(S.NullOr(S.String)),
+    google_maps_grounding_cost_per_query: S.optional(S.NullOr(S.Number)),
+    input_cost_per_audio_per_second: S.optional(S.NullOr(S.Number)),
+    input_cost_per_audio_per_second_above_128k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_audio_token: S.optional(S.NullOr(S.Number)),
+    input_cost_per_character: S.optional(S.NullOr(S.Number)),
+    input_cost_per_character_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_image: S.optional(S.NullOr(S.Number)),
+    input_cost_per_image_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_image_token: S.optional(S.NullOr(S.Number)),
+    input_cost_per_pixel: S.optional(S.NullOr(S.Number)),
+    input_cost_per_query: S.optional(S.NullOr(S.Number)),
+    input_cost_per_second: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_200k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_200k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_token_above_272k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_272k_tokens_flex: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_token_above_512k_tokens: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_batches: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_cache_hit: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_flex: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_priority: S.optional(S.NullOr(S.Number)),
+    input_cost_per_token_ultrafast: S.optional(S.NullOr(S.Number)),
+    input_cost_per_video_per_second: S.optional(S.NullOr(S.Number)),
+    input_cost_per_video_per_second_above_128k_tokens: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_video_per_second_above_15s_interval: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_video_per_second_above_8s_interval: S.optional(
+      S.NullOr(S.Number),
+    ),
+    input_cost_per_video_token: S.optional(S.NullOr(S.Number)),
+    itpm: S.optional(S.NullOr(S.Number)),
+    keepalive_seconds: S.optional(S.NullOr(S.Number)),
+    litellm_credential_name: S.optional(S.NullOr(S.String)),
+    litellm_trace_id: S.optional(S.NullOr(S.String)),
+    max_budget: S.optional(S.NullOr(S.Number)),
+    max_file_size_mb: S.optional(S.NullOr(S.Number)),
+    max_retries: S.optional(S.NullOr(S.Number)),
+    merge_reasoning_content_in_choices: S.optional(S.NullOr(S.Boolean)),
+    milvus_db_name: S.optional(S.NullOr(S.String)),
+    milvus_partition_names: S.optional(
+      S.NullOr(UpdateLiteLLMParamsMilvusPartitionNamesList),
+    ),
+    milvus_text_field: S.optional(S.NullOr(S.String)),
+    mock_response: S.optional(S.NullOr(UpdateLiteLLMParamsMockResponse)),
+    model: S.optional(S.NullOr(S.String)),
+    model_info: S.optional(S.NullOr(UpdateLiteLLMParamsModelInfoMap)),
+    ocr_cost_per_credit: S.optional(S.NullOr(S.Number)),
+    ocr_cost_per_page: S.optional(S.NullOr(S.Number)),
+    organization: S.optional(S.NullOr(S.String)),
+    otpm: S.optional(S.NullOr(S.Number)),
+    output_cost_per_audio_per_second: S.optional(S.NullOr(S.Number)),
+    output_cost_per_audio_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_character: S.optional(S.NullOr(S.Number)),
+    output_cost_per_character_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_image: S.optional(S.NullOr(S.Number)),
+    output_cost_per_image_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_pixel: S.optional(S.NullOr(S.Number)),
+    output_cost_per_reasoning_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_reasoning_token_flex: S.optional(S.NullOr(S.Number)),
+    output_cost_per_reasoning_token_priority: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second_1080p: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second_480p: S.optional(S.NullOr(S.Number)),
+    output_cost_per_second_4k: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_128k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_200k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_200k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    output_cost_per_token_above_272k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_above_272k_tokens_flex: S.optional(
+      S.NullOr(S.Number),
+    ),
+    output_cost_per_token_above_272k_tokens_priority: S.optional(
+      S.NullOr(S.Number),
+    ),
+    output_cost_per_token_above_512k_tokens: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_batches: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_flex: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_priority: S.optional(S.NullOr(S.Number)),
+    output_cost_per_token_ultrafast: S.optional(S.NullOr(S.Number)),
+    output_cost_per_video_per_second: S.optional(S.NullOr(S.Number)),
+    output_cost_per_video_token: S.optional(S.NullOr(S.Number)),
+    output_vector_size: S.optional(S.NullOr(S.Number)),
+    quality_router_config: S.optional(
+      S.NullOr(UpdateLiteLLMParamsQualityRouterConfigMap),
+    ),
+    quality_router_default_model: S.optional(S.NullOr(S.String)),
+    region_name: S.optional(S.NullOr(S.String)),
+    regional_endpoint_uplift_multiplier: S.optional(S.NullOr(S.Number)),
+    regional_processing_uplift_multiplier_eu: S.optional(S.NullOr(S.Number)),
+    regional_processing_uplift_multiplier_us: S.optional(S.NullOr(S.Number)),
+    rpm: S.optional(S.NullOr(S.Number)),
+    s3_bucket_name: S.optional(S.NullOr(S.String)),
+    s3_encryption_key_id: S.optional(S.NullOr(S.String)),
+    s3_output_bucket_name: S.optional(S.NullOr(S.String)),
+    s3_region_name: S.optional(S.NullOr(S.String)),
+    search_context_cost_per_query: S.optional(
+      S.NullOr(UpdateLiteLLMParamsSearchContextCostPerQueryMap),
+    ),
+    stream_timeout: S.optional(S.NullOr(UpdateLiteLLMParamsStreamTimeout)),
+    tag_regex: S.optional(S.NullOr(UpdateLiteLLMParamsTagRegexList)),
+    tags: S.optional(S.NullOr(UpdateLiteLLMParamsTagsList)),
+    tiered_pricing: S.optional(S.NullOr(UpdateLiteLLMParamsTieredPricingList)),
+    timeout: S.optional(S.NullOr(UpdateLiteLLMParamsTimeout)),
+    tpm: S.optional(S.NullOr(S.Number)),
+    use_chat_completions_api: S.optional(S.NullOr(S.Boolean)),
+    use_in_pass_through: S.optional(S.NullOr(S.Boolean)),
+    use_litellm_proxy: S.optional(S.NullOr(S.Boolean)),
+    use_xai_oauth: S.optional(S.NullOr(S.Boolean)),
+    valkey_embedding_field: S.optional(S.NullOr(S.String)),
+    valkey_host: S.optional(S.NullOr(S.String)),
+    valkey_password: S.optional(S.NullOr(S.String)),
+    valkey_port: S.optional(S.NullOr(S.Number)),
+    valkey_ssl: S.optional(S.NullOr(S.Boolean)),
+    valkey_text_field: S.optional(S.NullOr(S.String)),
+    vector_store_id: S.optional(S.NullOr(S.String)),
+    vertex_credentials: S.optional(
+      S.NullOr(UpdateLiteLLMParamsVertexCredentials),
+    ),
+    vertex_location: S.optional(S.NullOr(S.String)),
+    vertex_project: S.optional(S.NullOr(S.String)),
+    watsonx_region_name: S.optional(S.NullOr(S.String)),
+  }),
+).annotate({
+  identifier: "UpdateLiteLLMParams",
+}) as any as S.Schema<UpdateLiteLLMParams>;
+
+export interface PatchModelModelModelIdUpdatePatchRequest {
+  model_id: string;
+  blocked?: boolean | null;
+  litellm_params?: UpdateLiteLLMParams | null;
+  model_info?: LitellmTypesRouterModelInfo | null;
+  model_name?: string | null;
+}
+export const PatchModelModelModelIdUpdatePatchRequest = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      model_id: S.String.pipe(T.Label()),
+      blocked: S.optional(S.NullOr(S.Boolean)),
+      litellm_params: S.optional(S.NullOr(UpdateLiteLLMParams)),
+      model_info: S.optional(S.NullOr(LitellmTypesRouterModelInfo)),
+      model_name: S.optional(S.NullOr(S.String)),
+    }).pipe(
+      T.Http({ method: "PATCH", uri: "/model/{model_id}/update", code: 200 }),
+    ),
+).annotate({
+  identifier: "PatchModelModelModelIdUpdatePatchRequest",
+}) as any as S.Schema<PatchModelModelModelIdUpdatePatchRequest>;
+
+export interface PatchModelModelModelIdUpdatePatchResponse {
+  body: unknown;
+}
+export const PatchModelModelModelIdUpdatePatchResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "PatchModelModelModelIdUpdatePatchResponse",
+  }) as any as S.Schema<PatchModelModelModelIdUpdatePatchResponse>;
+
+export interface PostBlockModelModelBlockRequest {
+  model_id: string;
+}
+export const PostBlockModelModelBlockRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    model_id: S.String,
+  }).pipe(T.Http({ method: "POST", uri: "/model/block", code: 200 })),
+).annotate({
+  identifier: "PostBlockModelModelBlockRequest",
+}) as any as S.Schema<PostBlockModelModelBlockRequest>;
+
+export type LiteLLMProxyModelTableLitellmParamsMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMProxyModelTableLitellmParamsMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMProxyModelTableLitellmParamsMap>;
+
+export type LiteLLMProxyModelTableModelInfoMap = {
+  [key: string]: unknown | undefined;
+};
+export const LiteLLMProxyModelTableModelInfoMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<LiteLLMProxyModelTableModelInfoMap>;
+
+export interface LiteLLMProxyModelTable {
+  blocked?: boolean;
+  created_at?: string | null;
+  created_by?: string | null;
+  litellm_params: LiteLLMProxyModelTableLitellmParamsMap;
+  model_id: string;
+  model_info?: LiteLLMProxyModelTableModelInfoMap | null;
+  model_name: string;
+  updated_at?: string | null;
+  updated_by?: string | null;
+}
+export const LiteLLMProxyModelTable = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    blocked: S.optional(S.Boolean),
+    created_at: S.optional(S.NullOr(S.String)),
+    created_by: S.optional(S.NullOr(S.String)),
+    litellm_params: LiteLLMProxyModelTableLitellmParamsMap,
+    model_id: S.String,
+    model_info: S.optional(S.NullOr(LiteLLMProxyModelTableModelInfoMap)),
+    model_name: S.String,
+    updated_at: S.optional(S.NullOr(S.String)),
+    updated_by: S.optional(S.NullOr(S.String)),
+  }),
+).annotate({
+  identifier: "LiteLLMProxyModelTable",
+}) as any as S.Schema<LiteLLMProxyModelTable>;
+
+export interface PostBlockModelModelBlockResponse {
+  body: LiteLLMProxyModelTable | null;
+}
+export const PostBlockModelModelBlockResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.NullOr(LiteLLMProxyModelTable),
+  }),
+).annotate({
+  identifier: "PostBlockModelModelBlockResponse",
+}) as any as S.Schema<PostBlockModelModelBlockResponse>;
+
+/** An operator-defined tier: the name the LLM classifier must return and its rubric description. */
+export interface TierDefinition {
+  /** What belongs in this tier; rendered as this tier's bullet in the classifier rubric. Required unless the name is a built-in tier (SIMPLE/MEDIUM/COMPLEX/REASONING), which inherits the built-in criteria when omitted */
+  description?: string | null;
+  /** Tier name; becomes a value the LLM classifier can return and a key of `tiers` */
+  name: string;
+}
+export const TierDefinition = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    description: S.optional(S.NullOr(S.String)),
+    name: S.String,
+  }),
+).annotate({ identifier: "TierDefinition" }) as any as S.Schema<TierDefinition>;
+
+export type PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequestTierDefinitionsList =
+  Array<TierDefinition>;
+export const PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequestTierDefinitionsList =
+  /*@__PURE__*/ S.Array(
+    TierDefinition,
+  ) as any as S.Schema<PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequestTierDefinitionsList>;
+
+export interface PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequest {
+  classification_prompt?: string | null;
+  context_window_size?: number;
+  tier_definitions: PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequestTierDefinitionsList;
+}
+export const PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      classification_prompt: S.optional(S.NullOr(S.String)),
+      context_window_size: S.optional(S.Number),
+      tier_definitions:
+        PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequestTierDefinitionsList,
+    }).pipe(
+      T.Http({
+        method: "POST",
+        uri: "/auto_router/classifier/default_prompt",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequest",
+  }) as any as S.Schema<PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequest>;
+
+/** When adaptive=True: 'all' scores every pool model with a tier-distance penalty (soft floors); 'classified_tier' Thompson-samples only inside the classified tier's pool */
+export type RequestComplexityRouterConfigAdaptiveEligible =
+  | "all"
+  | "classified_tier";
+export const RequestComplexityRouterConfigAdaptiveEligible = S.String;
+
+export interface AdaptiveRouterWeights {
+  cost?: number;
+  quality?: number;
+}
+export const AdaptiveRouterWeights = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    cost: S.optional(S.Number),
+    quality: S.optional(S.Number),
+  }),
+).annotate({
+  identifier: "AdaptiveRouterWeights",
+}) as any as S.Schema<AdaptiveRouterWeights>;
+
+/** What classifies the request when the LLM classifier errors, times out, or returns an unparseable response. 'heuristic' runs the local complexity scorer, which is right when the classifier grades complexity too. 'default_model' skips scoring and routes to default_model, which is what a classifier on some other taxonomy wants: a prompt that grades data sensitivity has no use for a complexity score, and scoring one produces a tier unrelated to what the operator configured. Requires default_model when set to 'default_model'. Only applies when classifier_type is 'llm', 'custom', or 'heuristic_first'. */
+export type RequestComplexityRouterConfigClassifierFallback =
+  | "heuristic"
+  | "default_model";
+export const RequestComplexityRouterConfigClassifierFallback = S.String;
+
+/** Configuration for the LLM-based complexity classifier. */
+export interface ClassifierLLMConfig {
+  /** Which calibration examples the built-in rubric carries. 'agentic' anchors routine installs, builds, multi-file edits, and standard debugging at MEDIUM, so ordinary engineering does not route to the most expensive tier; it suits agent, terminal, and coding-assistant traffic as well as mixed traffic. 'chat' omits those engineering anchors, for a deployment serving only conversational traffic. 'business' carries business/sales anchors and business-flavored tier criteria that keep routine drafting and summarizing off the expensive tiers and reserve the top tier for committing to decisions under tradeoffs; it suits sales, support, and go-to-market traffic. Every preset keeps the same four tiers, so this moves where the boundary sits without changing the taxonomy. Leave unset for 'legacy', the rubric as it shipped before calibration examples existed, so an existing router's tier decisions and spend do not move on upgrade. Mutually exclusive with system_prompt, which replaces the rubric this would select. Only applies when classifier_type is 'llm'. */
+  classification_rubric?: ClassificationRubric | (string & {}) | null;
+  /** Model name (from the router's model_list) to call for classification */
+  model: string;
+  /** Replaces the built-in complexity rubric as the classifier's entire system role. When set, neither the default rubric nor the context-window closing line is appended, so the prompt owns the whole taxonomy and the tier names SIMPLE/MEDIUM/COMPLEX/REASONING become whatever buckets it defines: a prompt that classifies data sensitivity routes on that instead of on difficulty. Two consequences of full replacement. The default rubric's closing paragraph is the classifier's prompt-injection defense, telling it that the caller's quoted system prompt and prior turns are material to judge and never instructions; a replacement that omits it lets a caller ask for a tier and get it. And the heuristic fallback still scores complexity, so a router on some other taxonomy wants classifier_fallback='default_model'. Leave unset for the built-in rubric. Only applies when classifier_type is 'llm'. */
+  system_prompt?: string | null;
+  /** Timeout budget for the classification call, in milliseconds */
+  timeout_ms?: number;
+}
+export const ClassifierLLMConfig = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    classification_rubric: S.optional(S.NullOr(ClassificationRubric)),
+    model: S.String,
+    system_prompt: S.optional(S.NullOr(S.String)),
+    timeout_ms: S.optional(S.Number),
+  }),
+).annotate({
+  identifier: "ClassifierLLMConfig",
+}) as any as S.Schema<ClassifierLLMConfig>;
+
+/** Classification strategy: local regex/keyword scoring, an LLM call, a custom classifier plugin, or 'heuristic_first', which scores locally and only pays for the LLM classifier when the local scorer does not confidently land a cheap tier */
+export type RequestComplexityRouterConfigClassifierType =
+  | "heuristic"
+  | "llm"
+  | "custom"
+  | "heuristic_first";
+export const RequestComplexityRouterConfigClassifierType = S.String;
+
+export type RequestComplexityRouterConfigCodeKeywordsList = Array<string>;
+export const RequestComplexityRouterConfigCodeKeywordsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigCodeKeywordsList>;
+
+export type RequestComplexityRouterConfigCustomTechnicalKeywordsList =
+  Array<string>;
+export const RequestComplexityRouterConfigCustomTechnicalKeywordsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigCustomTechnicalKeywordsList>;
+
+/** Weights for each scoring dimension */
+export type RequestComplexityRouterConfigDimensionWeightsMap = {
+  [key: string]: number | undefined;
+};
+export const RequestComplexityRouterConfigDimensionWeightsMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Number,
+  ) as any as S.Schema<RequestComplexityRouterConfigDimensionWeightsMap>;
+
+export type RequestComplexityRouterConfigEscalationKeywordsList = Array<string>;
+export const RequestComplexityRouterConfigEscalationKeywordsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigEscalationKeywordsList>;
+
+export type RequestComplexityRouterConfigHousekeepingPatternsList =
+  Array<string>;
+export const RequestComplexityRouterConfigHousekeepingPatternsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigHousekeepingPatternsList>;
+
+/** Keywords/phrases that trigger this rule (lexical or semantic match) */
+export type KeywordTierRuleKeywordsList = Array<string>;
+export const KeywordTierRuleKeywordsList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<KeywordTierRuleKeywordsList>;
+
+/** A deterministic override: if any keyword matches, route to this tier. */
+export interface KeywordTierRule {
+  /** Keywords/phrases that trigger this rule (lexical or semantic match) */
+  keywords: KeywordTierRuleKeywordsList;
+  /** Tier to route to when this rule matches: a built-in tier name, or with tier_definitions set, one of the defined tier names */
+  tier: string;
+}
+export const KeywordTierRule = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    keywords: KeywordTierRuleKeywordsList,
+    tier: S.String,
+  }),
+).annotate({
+  identifier: "KeywordTierRule",
+}) as any as S.Schema<KeywordTierRule>;
+
+export type RequestComplexityRouterConfigKeywordTierRulesList =
+  Array<KeywordTierRule>;
+export const RequestComplexityRouterConfigKeywordTierRulesList =
+  /*@__PURE__*/ S.Array(
+    KeywordTierRule,
+  ) as any as S.Schema<RequestComplexityRouterConfigKeywordTierRulesList>;
+
+export type RequestComplexityRouterConfigPlanModePatternsList = Array<string>;
+export const RequestComplexityRouterConfigPlanModePatternsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigPlanModePatternsList>;
+
+export type RequestComplexityRouterConfigReasoningKeywordsList = Array<string>;
+export const RequestComplexityRouterConfigReasoningKeywordsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigReasoningKeywordsList>;
+
+/** One open/close delimiter pair a harness wraps injected context in. Normalizing here rather than at the scan is what makes matching case-insensitive: markers reach the scan already lowered, so it lowercases only the haystack and never the needles. Stripping keeps YAML indentation whitespace from becoming part of the delimiter. */
+export interface ReminderMarkerPair {
+  /** Closing delimiter, e.g. '</system-reminder>' */
+  close: string;
+  /** Opening delimiter, e.g. '<system-reminder>' */
+  open: string;
+}
+export const ReminderMarkerPair = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    close: S.String,
+    open: S.String,
+  }),
+).annotate({
+  identifier: "ReminderMarkerPair",
+}) as any as S.Schema<ReminderMarkerPair>;
+
+export type RequestComplexityRouterConfigReminderMarkersList =
+  Array<ReminderMarkerPair>;
+export const RequestComplexityRouterConfigReminderMarkersList =
+  /*@__PURE__*/ S.Array(
+    ReminderMarkerPair,
+  ) as any as S.Schema<RequestComplexityRouterConfigReminderMarkersList>;
+
+export type RequestComplexityRouterConfigSimpleKeywordsList = Array<string>;
+export const RequestComplexityRouterConfigSimpleKeywordsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigSimpleKeywordsList>;
+
+export type RequestComplexityRouterConfigTechnicalKeywordsList = Array<string>;
+export const RequestComplexityRouterConfigTechnicalKeywordsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigTechnicalKeywordsList>;
+
+/** Score boundaries between tiers. These keys (simple_medium, medium_complex, complex_reasoning) name the gaps between the default tier names and are not renameable by tier_labels; they are scorer knobs persisted by name on every routing decision */
+export type RequestComplexityRouterConfigTierBoundariesMap = {
+  [key: string]: number | undefined;
+};
+export const RequestComplexityRouterConfigTierBoundariesMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Number,
+  ) as any as S.Schema<RequestComplexityRouterConfigTierBoundariesMap>;
+
+export type RequestComplexityRouterConfigTierDefinitionsList =
+  Array<TierDefinition>;
+export const RequestComplexityRouterConfigTierDefinitionsList =
+  /*@__PURE__*/ S.Array(
+    TierDefinition,
+  ) as any as S.Schema<RequestComplexityRouterConfigTierDefinitionsList>;
+
+/** Display names for the complexity tiers, so a deployment can use its own vocabulary (e.g. Cheap/Standard/Premium/Deep) in the dashboard, spend logs, and the LLM classifier rubric. Purely operator-facing: config keys stay canonical (tiers, keyword_tier_rules[].tier, tier_boundaries), API callers never see these names, and the heuristic scorer never reads them. Unlisted tiers keep their canonical name. Partial maps are allowed. */
+export type RequestComplexityRouterConfigTierLabelsMap = {
+  [key: string]: string | undefined;
+};
+export const RequestComplexityRouterConfigTierLabelsMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigTierLabelsMap>;
+
+export type ComplexityTierModelLitellmParamsMap = {
+  [key: string]: unknown | undefined;
+};
+export const ComplexityTierModelLitellmParamsMap = /*@__PURE__*/ S.Record(
+  S.String,
+  S.Unknown,
+) as any as S.Schema<ComplexityTierModelLitellmParamsMap>;
+
+export interface ComplexityTierModel {
+  litellm_params?: ComplexityTierModelLitellmParamsMap;
+  model_name: string;
+}
+export const ComplexityTierModel = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    litellm_params: S.optional(ComplexityTierModelLitellmParamsMap),
+    model_name: S.String,
+  }),
+).annotate({
+  identifier: "ComplexityTierModel",
+}) as any as S.Schema<ComplexityTierModel>;
+
+export type RequestComplexityRouterConfigTierModelConfigsValueList =
+  Array<ComplexityTierModel>;
+export const RequestComplexityRouterConfigTierModelConfigsValueList =
+  /*@__PURE__*/ S.Array(
+    ComplexityTierModel,
+  ) as any as S.Schema<RequestComplexityRouterConfigTierModelConfigsValueList>;
+
+export type RequestComplexityRouterConfigTierModelConfigsMap = {
+  [key: string]:
+    | RequestComplexityRouterConfigTierModelConfigsValueList
+    | undefined;
+};
+export const RequestComplexityRouterConfigTierModelConfigsMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    RequestComplexityRouterConfigTierModelConfigsValueList,
+  ) as any as S.Schema<RequestComplexityRouterConfigTierModelConfigsMap>;
+
+export type RequestComplexityRouterConfigTiersValueCase1List = Array<string>;
+export const RequestComplexityRouterConfigTiersValueCase1List =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<RequestComplexityRouterConfigTiersValueCase1List>;
+
+export type RequestComplexityRouterConfigTiersValue =
+  | string
+  | RequestComplexityRouterConfigTiersValueCase1List;
+export const RequestComplexityRouterConfigTiersValue =
+  S.Unknown as any as S.Schema<RequestComplexityRouterConfigTiersValue>;
+
+/** Mapping of complexity tiers to a model or model pool. A list is randomly picked from when adaptive=False, and used as a soft-floor home pool when adaptive=True */
+export type RequestComplexityRouterConfigTiersMap = {
+  [key: string]: RequestComplexityRouterConfigTiersValue | undefined;
+};
+export const RequestComplexityRouterConfigTiersMap = /*@__PURE__*/ S.Record(
+  S.String,
+  RequestComplexityRouterConfigTiersValue,
+) as any as S.Schema<RequestComplexityRouterConfigTiersMap>;
+
+/** Token count thresholds for simple/complex classification */
+export type RequestComplexityRouterConfigTokenThresholdsMap = {
+  [key: string]: number | undefined;
+};
+export const RequestComplexityRouterConfigTokenThresholdsMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Number,
+  ) as any as S.Schema<RequestComplexityRouterConfigTokenThresholdsMap>;
+
+/** The part of a complexity-router config a request can carry. `plugins` holds live RoutingPlugin objects, which no JSON body can express and which have no OpenAPI schema, so it is closed off here rather than left as an arbitrary-type field. */
+export interface RequestComplexityRouterConfig {
+  /** Enable adaptive bandit selection with soft complexity floors */
+  adaptive?: boolean;
+  /** When adaptive=True: 'all' scores every pool model with a tier-distance penalty (soft floors); 'classified_tier' Thompson-samples only inside the classified tier's pool */
+  adaptive_eligible?:
+    | RequestComplexityRouterConfigAdaptiveEligible
+    | (string & {});
+  /** Quality vs cost weights for adaptive selection (used when adaptive=True) */
+  adaptive_weights?: AdaptiveRouterWeights;
+  /** Replaces the opening instructions of the LLM classifier rubric (the judging-criteria prose) for a custom tier set. The per-tier bullets and the trust-boundary paragraph telling the classifier to ignore tier requests embedded in quoted caller text are always appended after it and cannot be overridden. Requires tier_definitions; a built-in-tier router customizes its prompt via classifier_llm_config.system_prompt or classification_rubric instead. */
+  classification_prompt?: string | null;
+  /** Maximum characters of prior-turn text quoted to the LLM classifier, across the whole context window, per classification call. Turns are taken newest first and quoted whole while they fit, so a conversation small enough to quote entirely is never cut; once the budget runs out the older turns are dropped whole and only the turn straddling the boundary is truncated, into whatever space is left. The current ask and the caller's system prompt sit outside this budget and are always sent in full, as does the numbering each quoted turn carries. A budget under 120 leaves no room to quote a turn and suppresses the block; set classifier_context_window_size to 0 to turn context off deliberately. Only applies when classifier_type is 'llm'. */
+  classifier_context_budget_chars?: number;
+  /** Include assistant turns in the classifier context window, so difficulty stated by the model rather than by the user stays visible: a plan the assistant calls complex, which the user approves with 'yes', is classified on the work being approved instead of on the word 'yes'. When enabled, classifier_context_window_size counts the last N turns of the conversation across both roles rather than the last N user turns, and assistant text is sent to the classifier model, which may be a different deployment or provider than the routed completion model. Assistant replies spend classifier_context_budget_chars alongside user turns, so raise it if the oldest turns stop being quoted once replies join the window. Off by default because enabling it shifts tier decisions, and therefore spend, for an already-deployed router. Only applies when classifier_type is 'llm'. */
+  classifier_context_include_assistant_turns?: boolean;
+  /** Optional cap on each individual prior turn's text, applied before classifier_context_budget_chars bounds the block. Unset by default, so one long turn may spend the whole budget, which is usually what a follow-up needs; set it when no single turn should dominate the context the classifier sees. A capped turn keeps its opening and its ending with the middle elided. Only applies when classifier_type is 'llm'. */
+  classifier_context_per_turn_chars?: number | null;
+  /** Number of prior user turns (tool output and harness reminders excluded) to include as context in the LLM classifier prompt, so a follow-up like 'now do the same for the streaming path' is classified against what it refers to. Counts turns of both roles when classifier_context_include_assistant_turns is enabled. These turns are sent to the classifier model, which may be a different deployment or provider than the routed completion model; that call already carries the current user ask and the caller's system prompt in full. Set to 0 to send neither prior turns nor any conversation context beyond the current ask. Only applies when classifier_type is 'llm'. */
+  classifier_context_window_size?: number;
+  /** What classifies the request when the LLM classifier errors, times out, or returns an unparseable response. 'heuristic' runs the local complexity scorer, which is right when the classifier grades complexity too. 'default_model' skips scoring and routes to default_model, which is what a classifier on some other taxonomy wants: a prompt that grades data sensitivity has no use for a complexity score, and scoring one produces a tier unrelated to what the operator configured. Requires default_model when set to 'default_model'. Only applies when classifier_type is 'llm', 'custom', or 'heuristic_first'. */
+  classifier_fallback?:
+    | RequestComplexityRouterConfigClassifierFallback
+    | (string & {});
+  /** Configuration for the LLM classifier; required when classifier_type is 'llm' or 'heuristic_first' */
+  classifier_llm_config?: ClassifierLLMConfig | null;
+  /** Not settable over HTTP; the classifier plugin is a runtime object */
+  classifier_plugin?: unknown | null;
+  /** Timeout budget for the classifier plugin call, in milliseconds. On expiry the fallback path decides the tier. Only applies when classifier_type is 'custom'. */
+  classifier_plugin_timeout_ms?: number;
+  /** Classification strategy: local regex/keyword scoring, an LLM call, a custom classifier plugin, or 'heuristic_first', which scores locally and only pays for the LLM classifier when the local scorer does not confidently land a cheap tier */
+  classifier_type?: RequestComplexityRouterConfigClassifierType | (string & {});
+  /** Keywords indicating code-related content */
+  code_keywords?: RequestComplexityRouterConfigCodeKeywordsList | null;
+  /** Domain-specific technical keywords appended to the effective base list (technical_keywords if set, otherwise DEFAULT_TECHNICAL_KEYWORDS). Order is preserved; duplicates are removed case-insensitively against the base list and within this list. */
+  custom_technical_keywords?: RequestComplexityRouterConfigCustomTechnicalKeywordsList | null;
+  /** Default model to use if tier cannot be determined */
+  default_model?: string | null;
+  /** When True and a session_id is resolvable on the request, pin the deployment chosen inside each routed model group and reuse it whenever the session returns to that group, without pinning which group the session routes to. Independent of session_affinity, which pins the model group instead (and always carries this deployment pin with it): with session_affinity off, every turn is still classified on its own merits while a session that escalates to a stronger tier and comes back still lands on the deployment it used before, which is what keeps a provider prompt cache warm. Pins are held per model group, so switching tiers does not disturb the pin left behind in the previous group. On by default because re-shuffling a conversation across deployments of the same model discards that cache for no benefit; set False to keep every turn load-balanced across the group, which is what a deployment set with tight per-deployment rate limits wants. Inert when no session_id is resolvable, since there is nothing to key a pin on, and suppressed when plugins are configured, for the same reason session_affinity is. */
+  deployment_affinity?: boolean;
+  /** Weights for each scoring dimension */
+  dimension_weights?: RequestComplexityRouterConfigDimensionWeightsMap;
+  /** Embedding model (LiteLLM model name) used when semantic_keyword_matching is enabled */
+  embedding_model?: string | null;
+  /** Case-sensitive phrases a user can include to force a bump to the next-higher complexity tier when they aren't satisfied with results (they can force a stronger model, but not choose which one). Defaults to ['LITELLM ESCALATE'] when unset; set to an empty list to disable. */
+  escalation_keywords?: RequestComplexityRouterConfigEscalationKeywordsList | null;
+  /** Tier routed to when the LLM classifier fails (timeout, provider error, or an unparseable reply). Required with tier_definitions and must name a defined tier; the heuristic scorer cannot produce custom tiers, so this replaces the heuristic fallback for custom tier sets. */
+  fallback_tier?: string | null;
+  /** The highest tier the local scorer may decide on its own; required when classifier_type is 'heuristic_first' and rejected otherwise. A request whose heuristic tier is at or below this one skips the LLM classifier and routes straight to that heuristic tier, so the classifier call is only paid for on traffic the scorer could not place cheaply. The scorer must also have produced at least one signal: a prompt where no dimension fired scores 0.0 and would otherwise land SIMPLE by default rather than by evidence, which is how a chained router would silently send unclassified traffic to the cheapest model. Names a built-in tier, and may not name the highest one, since that would make the LLM classifier unreachable. */
+  heuristic_first_max_tier?: string | null;
+  /** Additional case-sensitive literal sentinels that mark a request as client housekeeping, on top of the built-in conversation-title ones. For clients whose wording the built-ins don't cover, or after a client release changes its strings. */
+  housekeeping_patterns?: RequestComplexityRouterConfigHousekeepingPatternsList | null;
+  /** Rules that force a specific tier when their keywords match the prompt */
+  keyword_tier_rules?: RequestComplexityRouterConfigKeywordTierRulesList | null;
+  /** Minimum cosine similarity for a semantic keyword match */
+  match_threshold?: number;
+  /** When set, requests carrying a coding-agent plan-mode sentinel (Claude Code plan mode, VS Code Copilot Plan mode, Copilot CLI's exit_plan_mode tool) are routed to at least this tier: the classified tier still wins when it is higher, and the floor also overrides a session-affinity pin to a lower tier for exactly the turns carrying the sentinel, without rewriting the pin -- the first turn after plan mode exits routes as if plan mode had never happened. Names a built-in tier, or with tier_definitions set, one of the defined tier names (list order is ascending severity, same as keyword_tier_rules). Unset disables detection entirely. The sentinels ride in client-injected prompt text, so a caller who pastes one can spend up to this tier's models -- never down, and never outside the configured pools. */
+  plan_mode_min_tier?: string | null;
+  /** Additional case-sensitive literal sentinels that mark a request as plan mode, on top of the built-in Claude Code and Copilot ones. For clients whose plan-mode wording the built-ins don't cover, or after a client release changes its strings. */
+  plan_mode_patterns?: RequestComplexityRouterConfigPlanModePatternsList | null;
+  /** Not settable over HTTP; routing plugins are runtime objects */
+  plugins?: unknown | null;
+  /** Keywords indicating reasoning-required content */
+  reasoning_keywords?: RequestComplexityRouterConfigReasoningKeywordsList | null;
+  /** Minimum weighted score a request must reach before 2+ reasoning markers may promote it to the reasoning tier. Unset tracks tier_boundaries.simple_medium, so the override never rescues a request the scorer placed in the cheapest tier; 0 restores the unconditional override */
+  reasoning_override_min_score?: number | null;
+  /** Override the delimiter pairs used to recognize and strip harness-injected reminder blocks before classification. A harness that wraps injected context differently per agent type (main, subagent, cron) lists every pair it emits. Replaces, rather than adds to, the built-in default of ('<system-reminder>', '</system-reminder>'), so a harness that also emits that pair lists it too. Matching is case-insensitive. */
+  reminder_markers?: RequestComplexityRouterConfigReminderMarkersList | null;
+  /** Return the resolved raw model name in the response model field instead of the client-requested complexity-router alias */
+  return_raw_model_name?: boolean;
+  /** Route a coding agent's own housekeeping calls to the cheapest configured tier without classifying them. A client names the conversation by quoting the whole session and asking for a title, so the ask reads as the session's engineering work and lands on the most expensive tier, which is the reverse of what the call is worth. Detection is a literal match against client-owned sentinels on the newest ask only, so it cannot fire on an earlier turn, and it never lowers what anyone else asked for: a keyword_tier_rule or a session pin still decides instead, and an escalation keyword or the plan-mode floor still raises the tier from here. Only the classifier is displaced, and its call is skipped, so a matched request costs nothing to route. Set false to classify these calls like any other. */
+  route_housekeeping_to_cheapest_tier?: boolean;
+  /** Match keyword_tier_rules by embedding similarity instead of literal text */
+  semantic_keyword_matching?: boolean;
+  /** When True and a session_id is resolvable on the request, pin the model chosen on the session's first turn and reuse it for every later turn, skipping re-classification. Off by default so every turn is classified on its own merits and routed to the cheapest adequate tier. Set True to keep a multi-turn session on one model, which preserves provider prompt caches and avoids cross-model conversation-history errors. Always implies the deployment pin regardless of deployment_affinity: the session sticks to one deployment of the pinned model, since freezing the model while re-shuffling its deployments would still go cache-cold. */
+  session_affinity?: boolean;
+  /** TTL for the session affinity pin; refreshed on every cache hit. Bounds both the session_affinity model pin and the deployment_affinity deployment pin, so it measures idle time for the session's routing decisions rather than total session length */
+  session_affinity_ttl_seconds?: number;
+  /** Keywords indicating simple/basic queries */
+  simple_keywords?: RequestComplexityRouterConfigSimpleKeywordsList | null;
+  /** Keywords indicating technical content */
+  technical_keywords?: RequestComplexityRouterConfigTechnicalKeywordsList | null;
+  /** Score boundaries between tiers. These keys (simple_medium, medium_complex, complex_reasoning) name the gaps between the default tier names and are not renameable by tier_labels; they are scorer knobs persisted by name on every routing decision */
+  tier_boundaries?: RequestComplexityRouterConfigTierBoundariesMap;
+  /** Operator-defined tier set replacing the built-in SIMPLE/MEDIUM/COMPLEX/REASONING. Each entry's name becomes a value the LLM classifier can return and its description becomes that tier's rubric bullet; entries named after a built-in tier may omit the description and inherit the built-in criteria. List order is ascending severity and decides which tier wins when several keyword_tier_rules match. Requires classifier_type 'llm' or 'custom', a fallback_tier, and `tiers` keys matching the defined names exactly. Escalation, adaptive selection, session affinity, plugins, tier_labels, and the calibration-example rubric presets are unavailable with a custom tier set: the first four are built on the built-in tier ladder, and the last two rename or exemplify tiers the set replaces. */
+  tier_definitions?: RequestComplexityRouterConfigTierDefinitionsList | null;
+  /** Score penalty per tier-step away from the classified tier when adaptive=True */
+  tier_distance_penalty?: number;
+  /** Display names for the complexity tiers, so a deployment can use its own vocabulary (e.g. Cheap/Standard/Premium/Deep) in the dashboard, spend logs, and the LLM classifier rubric. Purely operator-facing: config keys stay canonical (tiers, keyword_tier_rules[].tier, tier_boundaries), API callers never see these names, and the heuristic scorer never reads them. Unlisted tiers keep their canonical name. Partial maps are allowed. */
+  tier_labels?: RequestComplexityRouterConfigTierLabelsMap;
+  tier_model_configs?: RequestComplexityRouterConfigTierModelConfigsMap;
+  /** Mapping of complexity tiers to a model or model pool. A list is randomly picked from when adaptive=False, and used as a soft-floor home pool when adaptive=True */
+  tiers?: RequestComplexityRouterConfigTiersMap;
+  /** Token count thresholds for simple/complex classification */
+  token_thresholds?: RequestComplexityRouterConfigTokenThresholdsMap;
+}
+export const RequestComplexityRouterConfig = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    adaptive: S.optional(S.Boolean),
+    adaptive_eligible: S.optional(
+      RequestComplexityRouterConfigAdaptiveEligible,
+    ),
+    adaptive_weights: S.optional(AdaptiveRouterWeights),
+    classification_prompt: S.optional(S.NullOr(S.String)),
+    classifier_context_budget_chars: S.optional(S.Number),
+    classifier_context_include_assistant_turns: S.optional(S.Boolean),
+    classifier_context_per_turn_chars: S.optional(S.NullOr(S.Number)),
+    classifier_context_window_size: S.optional(S.Number),
+    classifier_fallback: S.optional(
+      RequestComplexityRouterConfigClassifierFallback,
+    ),
+    classifier_llm_config: S.optional(S.NullOr(ClassifierLLMConfig)),
+    classifier_plugin: S.optional(S.NullOr(S.Unknown)),
+    classifier_plugin_timeout_ms: S.optional(S.Number),
+    classifier_type: S.optional(RequestComplexityRouterConfigClassifierType),
+    code_keywords: S.optional(
+      S.NullOr(RequestComplexityRouterConfigCodeKeywordsList),
+    ),
+    custom_technical_keywords: S.optional(
+      S.NullOr(RequestComplexityRouterConfigCustomTechnicalKeywordsList),
+    ),
+    default_model: S.optional(S.NullOr(S.String)),
+    deployment_affinity: S.optional(S.Boolean),
+    dimension_weights: S.optional(
+      RequestComplexityRouterConfigDimensionWeightsMap,
+    ),
+    embedding_model: S.optional(S.NullOr(S.String)),
+    escalation_keywords: S.optional(
+      S.NullOr(RequestComplexityRouterConfigEscalationKeywordsList),
+    ),
+    fallback_tier: S.optional(S.NullOr(S.String)),
+    heuristic_first_max_tier: S.optional(S.NullOr(S.String)),
+    housekeeping_patterns: S.optional(
+      S.NullOr(RequestComplexityRouterConfigHousekeepingPatternsList),
+    ),
+    keyword_tier_rules: S.optional(
+      S.NullOr(RequestComplexityRouterConfigKeywordTierRulesList),
+    ),
+    match_threshold: S.optional(S.Number),
+    plan_mode_min_tier: S.optional(S.NullOr(S.String)),
+    plan_mode_patterns: S.optional(
+      S.NullOr(RequestComplexityRouterConfigPlanModePatternsList),
+    ),
+    plugins: S.optional(S.NullOr(S.Unknown)),
+    reasoning_keywords: S.optional(
+      S.NullOr(RequestComplexityRouterConfigReasoningKeywordsList),
+    ),
+    reasoning_override_min_score: S.optional(S.NullOr(S.Number)),
+    reminder_markers: S.optional(
+      S.NullOr(RequestComplexityRouterConfigReminderMarkersList),
+    ),
+    return_raw_model_name: S.optional(S.Boolean),
+    route_housekeeping_to_cheapest_tier: S.optional(S.Boolean),
+    semantic_keyword_matching: S.optional(S.Boolean),
+    session_affinity: S.optional(S.Boolean),
+    session_affinity_ttl_seconds: S.optional(S.Number),
+    simple_keywords: S.optional(
+      S.NullOr(RequestComplexityRouterConfigSimpleKeywordsList),
+    ),
+    technical_keywords: S.optional(
+      S.NullOr(RequestComplexityRouterConfigTechnicalKeywordsList),
+    ),
+    tier_boundaries: S.optional(RequestComplexityRouterConfigTierBoundariesMap),
+    tier_definitions: S.optional(
+      S.NullOr(RequestComplexityRouterConfigTierDefinitionsList),
+    ),
+    tier_distance_penalty: S.optional(S.Number),
+    tier_labels: S.optional(RequestComplexityRouterConfigTierLabelsMap),
+    tier_model_configs: S.optional(
+      RequestComplexityRouterConfigTierModelConfigsMap,
+    ),
+    tiers: S.optional(RequestComplexityRouterConfigTiersMap),
+    token_thresholds: S.optional(
+      RequestComplexityRouterConfigTokenThresholdsMap,
+    ),
+  }),
+).annotate({
+  identifier: "RequestComplexityRouterConfig",
+}) as any as S.Schema<RequestComplexityRouterConfig>;
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesItemMap =
+  { [key: string]: unknown | undefined };
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesItemMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesItemMap>;
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesList =
+  Array<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesItemMap>;
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesList =
+  /*@__PURE__*/ S.Array(
+    PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesItemMap,
+  ) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesList>;
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1ItemMap =
+  { [key: string]: unknown | undefined };
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1ItemMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1ItemMap>;
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1List =
+  Array<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1ItemMap>;
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1List =
+  /*@__PURE__*/ S.Array(
+    PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1ItemMap,
+  ) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1List>;
+
+/** The top-level system prompt an Anthropic /v1/messages body carries beside its messages */
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystem =
+  | string
+  | PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystemCase1List;
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystem =
+  S.Unknown as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystem>;
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsItemMap =
+  { [key: string]: unknown | undefined };
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsItemMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsItemMap>;
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsList =
+  Array<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsItemMap>;
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsList =
+  /*@__PURE__*/ S.Array(
+    PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsItemMap,
+  ) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsList>;
+
+export interface PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequest {
+  /** The complexity router config to route against, in the shape /model/new accepts */
+  complexity_router_config: RequestComplexityRouterConfig;
+  /** Model to route to when no tier resolves, i.e. complexity_router_default_model */
+  default_model?: string | null;
+  /** The full message list to route, exactly as the serving path would receive it. Mutually exclusive with prompt */
+  messages?: PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesList | null;
+  /** A single ask to route, as an end user would send it. Mutually exclusive with messages */
+  prompt?: string | null;
+  /** Name reported as the router in the routing decision. Display only */
+  router_name?: string;
+  /** The top-level system prompt an Anthropic /v1/messages body carries beside its messages */
+  system?: PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystem | null;
+  /** Team the router is being created for. Required for a team admin, who may only test their own team's routers */
+  team_id?: string | null;
+  /** The tool definitions the request advertises, which decide whether the plan-mode floor applies */
+  tools?: PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsList | null;
+}
+export const PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      complexity_router_config: RequestComplexityRouterConfig,
+      default_model: S.optional(S.NullOr(S.String)),
+      messages: S.optional(
+        S.NullOr(
+          PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestMessagesList,
+        ),
+      ),
+      prompt: S.optional(S.NullOr(S.String)),
+      router_name: S.optional(S.String),
+      system: S.optional(
+        S.NullOr(
+          PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestSystem,
+        ),
+      ),
+      team_id: S.optional(S.NullOr(S.String)),
+      tools: S.optional(
+        S.NullOr(
+          PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequestToolsList,
+        ),
+      ),
+    }).pipe(
+      T.Http({ method: "POST", uri: "/auto_router/test_routing", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequest",
+  }) as any as S.Schema<PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequest>;
+
+export type StandardLoggingRoutingDecisionCause =
+  | "heuristic_scorer"
+  | "reasoning_override"
+  | "llm_classifier"
+  | "heuristic_first_short_circuit"
+  | "classifier_plugin"
+  | "classifier_fallback"
+  | "default_model_fallback"
+  | "literal_keyword_match"
+  | "semantic_keyword_match"
+  | "plan_mode"
+  | "housekeeping"
+  | "session_affinity_pin"
+  | "session_affinity_escalation"
+  | "default_fallback"
+  | "keyword"
+  | "quality_tier"
+  | "bandit";
+export const StandardLoggingRoutingDecisionCause = S.String;
+
+export type StandardLoggingRoutingDecisionRouterType =
+  | "complexity"
+  | "adaptive"
+  | "quality";
+export const StandardLoggingRoutingDecisionRouterType = S.String;
+
+export type StandardLoggingRoutingDecisionSignalsList = Array<string>;
+export const StandardLoggingRoutingDecisionSignalsList = /*@__PURE__*/ S.Array(
+  S.String,
+) as any as S.Schema<StandardLoggingRoutingDecisionSignalsList>;
+
+/** Snapshot of the complexity scorer's tier boundaries at decision time, so a historical spend log row stays explainable after the router config changes. */
+export interface StandardLoggingRoutingDecisionTierBoundaries {
+  complex_reasoning: number;
+  medium_complex: number;
+  simple_medium: number;
+}
+export const StandardLoggingRoutingDecisionTierBoundaries =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      complex_reasoning: S.Number,
+      medium_complex: S.Number,
+      simple_medium: S.Number,
+    }),
+  ).annotate({
+    identifier: "StandardLoggingRoutingDecisionTierBoundaries",
+  }) as any as S.Schema<StandardLoggingRoutingDecisionTierBoundaries>;
+
+export type StandardLoggingRoutingDecisionTierLitellmParamsMap = {
+  [key: string]: unknown | undefined;
+};
+export const StandardLoggingRoutingDecisionTierLitellmParamsMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<StandardLoggingRoutingDecisionTierLitellmParamsMap>;
+
+/** Per-request provenance for a pre-routing strategy (auto-router) decision. */
+export interface StandardLoggingRoutingDecision {
+  cause?: StandardLoggingRoutingDecisionCause;
+  classifier_cost?: number;
+  classifier_model?: string;
+  conversation_continuing?: boolean;
+  escalated?: boolean;
+  escalation_keyword?: string;
+  matched_keyword?: string;
+  reasoning_override_min_score?: number;
+  request_type?: string;
+  routed_model?: string;
+  router_model_name?: string;
+  router_type?: StandardLoggingRoutingDecisionRouterType;
+  savings_baseline_deployment_id?: string;
+  savings_baseline_model?: string;
+  score?: number;
+  signals?: StandardLoggingRoutingDecisionSignalsList;
+  tier?: string;
+  tier_boundaries?: StandardLoggingRoutingDecisionTierBoundaries;
+  tier_label?: string;
+  tier_litellm_params?: StandardLoggingRoutingDecisionTierLitellmParamsMap;
+}
+export const StandardLoggingRoutingDecision = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    cause: S.optional(StandardLoggingRoutingDecisionCause),
+    classifier_cost: S.optional(S.Number),
+    classifier_model: S.optional(S.String),
+    conversation_continuing: S.optional(S.Boolean),
+    escalated: S.optional(S.Boolean),
+    escalation_keyword: S.optional(S.String),
+    matched_keyword: S.optional(S.String),
+    reasoning_override_min_score: S.optional(S.Number),
+    request_type: S.optional(S.String),
+    routed_model: S.optional(S.String),
+    router_model_name: S.optional(S.String),
+    router_type: S.optional(StandardLoggingRoutingDecisionRouterType),
+    savings_baseline_deployment_id: S.optional(S.String),
+    savings_baseline_model: S.optional(S.String),
+    score: S.optional(S.Number),
+    signals: S.optional(StandardLoggingRoutingDecisionSignalsList),
+    tier: S.optional(S.String),
+    tier_boundaries: S.optional(StandardLoggingRoutingDecisionTierBoundaries),
+    tier_label: S.optional(S.String),
+    tier_litellm_params: S.optional(
+      StandardLoggingRoutingDecisionTierLitellmParamsMap,
+    ),
+  }),
+).annotate({
+  identifier: "StandardLoggingRoutingDecision",
+}) as any as S.Schema<StandardLoggingRoutingDecision>;
+
+/** Where one prompt would have been routed, and why. */
+export interface AutoRouterRoutingTestResponse {
+  /** The model group the router picked */
+  routed_model: string;
+  /** Whether routed_model is a model group available to the caller, scoped to team_id when given. Never confirms models the caller could not use */
+  routed_model_configured: boolean;
+  /** The decision record this request would have written to its log row */
+  routing_decision: StandardLoggingRoutingDecision;
+}
+export const AutoRouterRoutingTestResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    routed_model: S.String,
+    routed_model_configured: S.Boolean,
+    routing_decision: StandardLoggingRoutingDecision,
+  }),
+).annotate({
+  identifier: "AutoRouterRoutingTestResponse",
+}) as any as S.Schema<AutoRouterRoutingTestResponse>;
+
+export interface PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderRequest {}
+export const PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({
+        method: "POST",
+        uri: "/reload/anthropic_beta_headers",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderRequest",
+  }) as any as S.Schema<PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderRequest>;
+
+export interface PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderResponse {
+  body: unknown;
+}
+export const PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderResponse",
+  }) as any as S.Schema<PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderResponse>;
+
+export interface PostReloadModelCostMapReloadModelCostMapRequest {}
+export const PostReloadModelCostMapReloadModelCostMapRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({}).pipe(
+      T.Http({ method: "POST", uri: "/reload/model_cost_map", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "PostReloadModelCostMapReloadModelCostMapRequest",
+  }) as any as S.Schema<PostReloadModelCostMapReloadModelCostMapRequest>;
+
+export interface PostReloadModelCostMapReloadModelCostMapResponse {
+  body: unknown;
+}
+export const PostReloadModelCostMapReloadModelCostMapResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "PostReloadModelCostMapReloadModelCostMapResponse",
+  }) as any as S.Schema<PostReloadModelCostMapReloadModelCostMapResponse>;
+
+export interface PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadRequest {
+  hours: number;
+}
+export const PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      hours: S.Number.pipe(T.Query()),
+    }).pipe(
+      T.Http({
+        method: "POST",
+        uri: "/schedule/anthropic_beta_headers_reload",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadRequest",
+  }) as any as S.Schema<PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadRequest>;
+
+export interface PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadResponse {
+  body: unknown;
+}
+export const PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadResponse",
+  }) as any as S.Schema<PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadResponse>;
+
+export interface PostScheduleModelCostMapReloadScheduleModelCostMapReloadRequest {
+  hours: number;
+}
+export const PostScheduleModelCostMapReloadScheduleModelCostMapReloadRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      hours: S.Number.pipe(T.Query()),
+    }).pipe(
+      T.Http({
+        method: "POST",
+        uri: "/schedule/model_cost_map_reload",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "PostScheduleModelCostMapReloadScheduleModelCostMapReloadRequest",
+  }) as any as S.Schema<PostScheduleModelCostMapReloadScheduleModelCostMapReloadRequest>;
+
+export interface PostScheduleModelCostMapReloadScheduleModelCostMapReloadResponse {
+  body: unknown;
+}
+export const PostScheduleModelCostMapReloadScheduleModelCostMapReloadResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier:
+      "PostScheduleModelCostMapReloadScheduleModelCostMapReloadResponse",
+  }) as any as S.Schema<PostScheduleModelCostMapReloadScheduleModelCostMapReloadResponse>;
+
+export interface PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetRequest {
+  access_group: string;
+  budget_duration?: string | null;
+  budget_id?: string | null;
+  max_budget?: number | null;
+  soft_budget?: number | null;
+}
+export const PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String.pipe(T.Label()),
+      budget_duration: S.optional(S.NullOr(S.String)),
+      budget_id: S.optional(S.NullOr(S.String)),
+      max_budget: S.optional(S.NullOr(S.Number)),
+      soft_budget: S.optional(S.NullOr(S.Number)),
+    }).pipe(
+      T.Http({
+        method: "PUT",
+        uri: "/access_group/{access_group}/budget",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetRequest",
+  }) as any as S.Schema<PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetRequest>;
+
+export interface UnblockModelModelUnblockPostRequest {
+  model_id: string;
+}
+export const UnblockModelModelUnblockPostRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    model_id: S.String,
+  }).pipe(T.Http({ method: "POST", uri: "/model/unblock", code: 200 })),
+).annotate({
+  identifier: "UnblockModelModelUnblockPostRequest",
+}) as any as S.Schema<UnblockModelModelUnblockPostRequest>;
+
+export interface UnblockModelModelUnblockPostResponse {
+  body: LiteLLMProxyModelTable | null;
+}
+export const UnblockModelModelUnblockPostResponse = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      body: S.NullOr(LiteLLMProxyModelTable),
+    }),
+).annotate({
+  identifier: "UnblockModelModelUnblockPostResponse",
+}) as any as S.Schema<UnblockModelModelUnblockPostResponse>;
+
+export type UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelIdsList =
+  Array<string>;
+export const UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelIdsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelIdsList>;
+
+export type UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelNamesList =
+  Array<string>;
+export const UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelNamesList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelNamesList>;
+
+export interface UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequest {
+  access_group: string;
+  model_ids?: UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelIdsList | null;
+  model_names?: UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelNamesList | null;
+}
+export const UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      access_group: S.String.pipe(T.Label()),
+      model_ids: S.optional(
+        S.NullOr(
+          UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelIdsList,
+        ),
+      ),
+      model_names: S.optional(
+        S.NullOr(
+          UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequestModelNamesList,
+        ),
+      ),
+    }).pipe(
+      T.Http({
+        method: "PUT",
+        uri: "/access_group/{access_group}/update",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequest",
+  }) as any as S.Schema<UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequest>;
+
+export interface UpdateModelModelUpdatePostRequest {
+  blocked?: boolean | null;
+  litellm_params?: UpdateLiteLLMParams | null;
+  model_info?: LitellmTypesRouterModelInfo | null;
+  model_name?: string | null;
+}
+export const UpdateModelModelUpdatePostRequest = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    blocked: S.optional(S.NullOr(S.Boolean)),
+    litellm_params: S.optional(S.NullOr(UpdateLiteLLMParams)),
+    model_info: S.optional(S.NullOr(LitellmTypesRouterModelInfo)),
+    model_name: S.optional(S.NullOr(S.String)),
+  }).pipe(T.Http({ method: "POST", uri: "/model/update", code: 200 })),
+).annotate({
+  identifier: "UpdateModelModelUpdatePostRequest",
+}) as any as S.Schema<UpdateModelModelUpdatePostRequest>;
+
+export interface UpdateModelModelUpdatePostResponse {
+  body: unknown;
+}
+export const UpdateModelModelUpdatePostResponse = /*@__PURE__*/ S.suspend(() =>
+  S.Struct({
+    body: S.Unknown,
+  }),
+).annotate({
+  identifier: "UpdateModelModelUpdatePostResponse",
+}) as any as S.Schema<UpdateModelModelUpdatePostResponse>;
+
+/** List of model group names to make public */
+export type UpdatePublicModelGroupsModelGroupMakePublicPostRequestModelGroupsList =
+  Array<string>;
+export const UpdatePublicModelGroupsModelGroupMakePublicPostRequestModelGroupsList =
+  /*@__PURE__*/ S.Array(
+    S.String,
+  ) as any as S.Schema<UpdatePublicModelGroupsModelGroupMakePublicPostRequestModelGroupsList>;
+
+export interface UpdatePublicModelGroupsModelGroupMakePublicPostRequest {
+  /** List of model group names to make public */
+  model_groups: UpdatePublicModelGroupsModelGroupMakePublicPostRequestModelGroupsList;
+}
+export const UpdatePublicModelGroupsModelGroupMakePublicPostRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      model_groups:
+        UpdatePublicModelGroupsModelGroupMakePublicPostRequestModelGroupsList,
+    }).pipe(
+      T.Http({ method: "POST", uri: "/model_group/make_public", code: 200 }),
+    ),
+  ).annotate({
+    identifier: "UpdatePublicModelGroupsModelGroupMakePublicPostRequest",
+  }) as any as S.Schema<UpdatePublicModelGroupsModelGroupMakePublicPostRequest>;
+
+export interface UpdatePublicModelGroupsModelGroupMakePublicPostResponse {
+  body: unknown;
+}
+export const UpdatePublicModelGroupsModelGroupMakePublicPostResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "UpdatePublicModelGroupsModelGroupMakePublicPostResponse",
+  }) as any as S.Schema<UpdatePublicModelGroupsModelGroupMakePublicPostResponse>;
+
+export type UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValueCase1Map =
+  { [key: string]: unknown | undefined };
+export const UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValueCase1Map =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValueCase1Map>;
+
+export type UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValue =
+  | string
+  | UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValueCase1Map;
+export const UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValue =
+  S.Unknown as any as S.Schema<UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValue>;
+
+export type UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksMap =
+  {
+    [key: string]:
+      | UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValue
+      | undefined;
+  };
+export const UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksValue,
+  ) as any as S.Schema<UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksMap>;
+
+export interface UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequest {
+  useful_links: UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksMap;
+}
+export const UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      useful_links:
+        UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequestUsefulLinksMap,
+    }).pipe(
+      T.Http({
+        method: "POST",
+        uri: "/model_hub/update_useful_links",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier: "UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequest",
+  }) as any as S.Schema<UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequest>;
+
+export interface UpdateUsefulLinksModelHubUpdateUsefulLinksPostResponse {
+  body: unknown;
+}
+export const UpdateUsefulLinksModelHubUpdateUsefulLinksPostResponse =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      body: S.Unknown,
+    }),
+  ).annotate({
+    identifier: "UpdateUsefulLinksModelHubUpdateUsefulLinksPostResponse",
+  }) as any as S.Schema<UpdateUsefulLinksModelHubUpdateUsefulLinksPostResponse>;
+
+export type ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequestComplexityRouterConfigMap =
+  { [key: string]: unknown | undefined };
+export const ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequestComplexityRouterConfigMap =
+  /*@__PURE__*/ S.Record(
+    S.String,
+    S.Unknown,
+  ) as any as S.Schema<ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequestComplexityRouterConfigMap>;
+
+export interface ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequest {
+  complexity_router_config: ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequestComplexityRouterConfigMap;
+  /** Team the router is being created for. Required for a team admin, who may only validate their own team's routers */
+  team_id?: string | null;
+}
+export const ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequest =
+  /*@__PURE__*/ S.suspend(() =>
+    S.Struct({
+      complexity_router_config:
+        ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequestComplexityRouterConfigMap,
+      team_id: S.optional(S.NullOr(S.String)),
+    }).pipe(
+      T.Http({
+        method: "POST",
+        uri: "/auto_router/validate_complexity_router_config",
+        code: 200,
+      }),
+    ),
+  ).annotate({
+    identifier:
+      "ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequest",
+  }) as any as S.Schema<ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequest>;
+
+export interface ComplexityRouterConfigValidationResponse {
+  error?: string | null;
+  valid: boolean;
+}
+export const ComplexityRouterConfigValidationResponse = /*@__PURE__*/ S.suspend(
+  () =>
+    S.Struct({
+      error: S.optional(S.NullOr(S.String)),
+      valid: S.Boolean,
+    }),
+).annotate({
+  identifier: "ComplexityRouterConfigValidationResponse",
+}) as any as S.Schema<ComplexityRouterConfigValidationResponse>;
+
+export type AddNewModelModelNewPostError = UnprocessableEntity | LitellmOpError;
+/** Add New Model Allows adding new models to the model list in the config.yaml */
+export const addNewModelModelNewPost: API.OperationMethod<
+  AddNewModelModelNewPostRequest,
+  AddNewModelModelNewPostResponse,
+  AddNewModelModelNewPostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: AddNewModelModelNewPostRequest,
+  output: AddNewModelModelNewPostResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteError =
+  LitellmOpError;
+/** Cancel Anthropic Beta Headers Reload ADMIN ONLY / MASTER KEY Only Endpoint Cancel the scheduled periodic reload of the Anthropic beta headers configuration. */
+export const cancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDelete: API.OperationMethod<
+  CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteRequest,
+  CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteResponse,
+  CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input:
+    CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteRequest,
+  output:
+    CancelAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadDeleteResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type CancelModelCostMapReloadScheduleModelCostMapReloadDeleteError =
+  LitellmOpError;
+/** Cancel Model Cost Map Reload ADMIN ONLY / MASTER KEY Only Endpoint Cancel the scheduled periodic reload of the model cost map. */
+export const cancelModelCostMapReloadScheduleModelCostMapReloadDelete: API.OperationMethod<
+  CancelModelCostMapReloadScheduleModelCostMapReloadDeleteRequest,
+  CancelModelCostMapReloadScheduleModelCostMapReloadDeleteResponse,
+  CancelModelCostMapReloadScheduleModelCostMapReloadDeleteError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: CancelModelCostMapReloadScheduleModelCostMapReloadDeleteRequest,
+  output: CancelModelCostMapReloadScheduleModelCostMapReloadDeleteResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type CreateModelGroupAccessGroupNewPostError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Create Model Group Create a new access group containing multiple model names. An access group is a named collection of model groups that can be referenced by teams/keys for simplified access control. Example: ```bash curl -X POST 'http://localhost:4000/access_group/new' \ -H 'Authorization: Bearer sk-1234' \ -H 'Content-Type: application/json' \ -d '{ "access_group": "production-models", "model_names": ["gpt-4", "claude-3-opus", "gemini-pro"] }' ``` Parameters: - access_group: str - The access group name (e.g., "production-models") - model_names: List[str] - List of existing model groups to include Returns: - NewModelGroupResponse with the created access group details Raises: - HTTPException 400: If any model names don't exist - HTTPException 500: If database operations fail */
+export const createModelGroupAccessGroupNewPost: API.OperationMethod<
+  CreateModelGroupAccessGroupNewPostRequest,
+  NewModelGroupResponse,
+  CreateModelGroupAccessGroupNewPostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: CreateModelGroupAccessGroupNewPostRequest,
+  output: NewModelGroupResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Delete Access Group Delete an access group. Removes the access group from all deployments that have it. Example: ```bash curl -X DELETE 'http://localhost:4000/access_group/production-models/delete' \ -H 'Authorization: Bearer sk-1234' ``` Parameters: - access_group: str - The access group name (URL path parameter) Returns: - DeleteModelGroupResponse with deletion details Raises: - HTTPException 404: If access group not found */
+export const deleteAccessGroupAccessGroupAccessGroupDeleteDelete: API.OperationMethod<
+  DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteRequest,
+  DeleteModelGroupResponse,
+  DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: DeleteAccessGroupAccessGroupAccessGroupDeleteDeleteRequest,
+  output: DeleteModelGroupResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Delete Access Group Budget Clear the shared budget of an access group, leaving the group itself in place. Example: ```bash curl -X DELETE 'http://localhost:4000/access_group/production-models/budget' \ -H 'Authorization: Bearer sk-1234' ``` Parameters: - access_group: str - The access group name (URL path parameter) Returns: - DeleteAccessGroupBudgetResponse; budget_deleted is false when there was nothing to clear Raises: - HTTPException 404: If access group not found */
+export const deleteAccessGroupBudgetAccessGroupAccessGroupBudgetDelete: API.OperationMethod<
+  DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteRequest,
+  DeleteAccessGroupBudgetResponse,
+  DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: DeleteAccessGroupBudgetAccessGroupAccessGroupBudgetDeleteRequest,
+  output: DeleteAccessGroupBudgetResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type DeleteModelModelDeletePostError =
+  | BadRequest
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Delete Model Allows deleting models in the model list in the config.yaml */
+export const deleteModelModelDeletePost: API.OperationMethod<
+  DeleteModelModelDeletePostRequest,
+  DeleteModelModelDeletePostResponse,
+  DeleteModelModelDeletePostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: DeleteModelModelDeletePostRequest,
+  output: DeleteModelModelDeletePostResponse,
+  errors: [BadRequest, UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Get Access Group Budget Get the shared budget of an access group, and the spend drawn against it. Example: ```bash curl -X GET 'http://localhost:4000/access_group/production-models/budget' \ -H 'Authorization: Bearer sk-1234' ``` Parameters: - access_group: str - The access group name (URL path parameter) Returns: - AccessGroupBudgetResponse; budget is null when the group has no budget set Raises: - HTTPException 404: If access group not found */
+export const getAccessGroupBudgetAccessGroupAccessGroupBudgetGet: API.OperationMethod<
+  GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetRequest,
+  AccessGroupBudgetResponse,
+  GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetAccessGroupBudgetAccessGroupAccessGroupBudgetGetRequest,
+  output: AccessGroupBudgetResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetAccessGroupInfoAccessGroupAccessGroupInfoGetError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Get Access Group Info Get information about a specific access group. Example: ```bash curl -X GET 'http://localhost:4000/access_group/production-models/info' \ -H 'Authorization: Bearer sk-1234' ``` Parameters: - access_group: str - The access group name (URL path parameter) Returns: - AccessGroupInfo with the access group details, its shared budget and its spend Raises: - HTTPException 404: If access group not found */
+export const getAccessGroupInfoAccessGroupAccessGroupInfoGet: API.OperationMethod<
+  GetAccessGroupInfoAccessGroupAccessGroupInfoGetRequest,
+  AccessGroupInfo,
+  GetAccessGroupInfoAccessGroupAccessGroupInfoGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetAccessGroupInfoAccessGroupAccessGroupInfoGetRequest,
+  output: AccessGroupInfo,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetError =
+  LitellmOpError;
+/** Get Anthropic Beta Headers Reload Status ADMIN ONLY / MASTER KEY Only Endpoint Get the status of the scheduled Anthropic beta headers reload job. */
+export const getAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGet: API.OperationMethod<
+  GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetRequest,
+  GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetResponse,
+  GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input:
+    GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetRequest,
+  output:
+    GetAnthropicBetaHeadersReloadStatusScheduleAnthropicBetaHeadersReloadStatusGetResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Get Auto Router Classifier Default Prompt Get the built-in system prompt used by an auto-router's LLM classifier */
+export const getAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGet: API.OperationMethod<
+  GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetRequest,
+  AutoRouterClassifierDefaultPromptResponse,
+  GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input:
+    GetAutoRouterClassifierDefaultPromptAutoRouterClassifierDefaultPromptGetRequest,
+  output: AutoRouterClassifierDefaultPromptResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetError =
+  LitellmOpError;
+/** Get Model Cost Map Reload Status ADMIN ONLY / MASTER KEY Only Endpoint Get the status of the scheduled model cost map reload job. */
+export const getModelCostMapReloadStatusScheduleModelCostMapReloadStatusGet: API.OperationMethod<
+  GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetRequest,
+  GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetResponse,
+  GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetRequest,
+  output:
+    GetModelCostMapReloadStatusScheduleModelCostMapReloadStatusGetResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelCostMapSourceModelCostMapSourceGetError = LitellmOpError;
+/** Get Model Cost Map Source ADMIN ONLY / MASTER KEY Only Endpoint Returns information about where the current model cost/pricing data was loaded from. Response fields: - source: "local" (bundled backup) or "remote" (fetched from URL) - url: the remote URL that was attempted (null when env-forced local) - is_env_forced: true if LITELLM_LOCAL_MODEL_COST_MAP=True forced local usage - fallback_reason: human-readable reason why remote failed (null on success) - model_count: number of models in the currently loaded cost map */
+export const getModelCostMapSourceModelCostMapSourceGet: API.OperationMethod<
+  GetModelCostMapSourceModelCostMapSourceGetRequest,
+  GetModelCostMapSourceModelCostMapSourceGetResponse,
+  GetModelCostMapSourceModelCostMapSourceGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelCostMapSourceModelCostMapSourceGetRequest,
+  output: GetModelCostMapSourceModelCostMapSourceGetResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelDeprecationsModelDeprecationError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Deprecations List models with known deprecation/sunset dates, bucketed by urgency. Reads `deprecation_date` metadata from `model_prices_and_context_window.json` (and any per-deployment `model_info.deprecation_date` overrides) for the models configured on this proxy. Parameters: warn_within_days: Window (in days) used to bucket "imminent" models, 30 by default. Returns: A payload with three lists of `ModelDeprecationInfo` entries: - `deprecated`: deprecation date is in the past, so these requests may fail at any time. - `imminent`: deprecation date is within `warn_within_days` from today. - `upcoming`: deprecation date is further out. Example: ```shell curl -X GET 'http://localhost:4000/model/deprecations' \ -H 'Authorization: Bearer sk-1234' ``` */
+export const getModelDeprecationsModelDeprecation: API.OperationMethod<
+  GetModelDeprecationsModelDeprecationRequest,
+  ModelDeprecationResponse,
+  GetModelDeprecationsModelDeprecationError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelDeprecationsModelDeprecationRequest,
+  output: ModelDeprecationResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelDeprecationsV1ModelDeprecationError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Deprecations List models with known deprecation/sunset dates, bucketed by urgency. Reads `deprecation_date` metadata from `model_prices_and_context_window.json` (and any per-deployment `model_info.deprecation_date` overrides) for the models configured on this proxy. Parameters: warn_within_days: Window (in days) used to bucket "imminent" models, 30 by default. Returns: A payload with three lists of `ModelDeprecationInfo` entries: - `deprecated`: deprecation date is in the past, so these requests may fail at any time. - `imminent`: deprecation date is within `warn_within_days` from today. - `upcoming`: deprecation date is further out. Example: ```shell curl -X GET 'http://localhost:4000/model/deprecations' \ -H 'Authorization: Bearer sk-1234' ``` */
+export const getModelDeprecationsV1ModelDeprecation: API.OperationMethod<
+  GetModelDeprecationsV1ModelDeprecationRequest,
+  ModelDeprecationResponse,
+  GetModelDeprecationsV1ModelDeprecationError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelDeprecationsV1ModelDeprecationRequest,
+  output: ModelDeprecationResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelGroupInfoModelGroupInfoError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Group Info Get information about all the deployments on litellm proxy, including config.yaml descriptions (except api key and api base) - /model_group/info returns all model groups. End users of proxy should use /model_group/info since those models will be used for /chat/completions, /embeddings, etc. - /model_group/info?model_group=rerank-english-v3.0 returns all model groups for a specific model group (`model_name` in config.yaml) Example Request (All Models): ```shell curl -X 'GET' 'http://localhost:4000/model_group/info' -H 'accept: application/json' -H 'x-api-key: sk-1234' ``` Example Request (Specific Model Group): ```shell curl -X 'GET' 'http://localhost:4000/model_group/info?model_group=rerank-english-v3.0' -H 'accept: application/json' -H 'Authorization: Bearer sk-1234' ``` Example Request (Specific Wildcard Model Group): (e.g. `model_name: openai/*` on config.yaml) ```shell curl -X 'GET' 'http://localhost:4000/model_group/info?model_group=openai/tts-1' -H 'accept: application/json' -H 'Authorization: Bearersk-1234' ``` Learn how to use and set wildcard models [here](https://docs.litellm.ai/docs/wildcard_routing) Example Response: ```json { "data": [ { "model_group": "rerank-english-v3.0", "providers": [ "cohere" ], "max_input_tokens": null, "max_output_tokens": null, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "mode": null, "tpm": null, "rpm": null, "supports_parallel_function_calling": false, "supports_vision": false, "supports_function_calling": false, "supported_openai_params": [ "stream", "temperature", "max_tokens", "logit_bias", "top_p", "frequency_penalty", "presence_penalty", "stop", "n", "extra_headers" ] }, { "model_group": "gpt-3.5-turbo", "providers": [ "openai" ], "max_input_tokens": 16385.0, "max_output_tokens": 4096.0, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 2e-06, "mode": "chat", "tpm": null, "rpm": null, "supports_parallel_function_calling": false, "supports_vision": false, "supports_function_calling": true, "supported_openai_params": [ "frequency_penalty", "logit_bias", "logprobs", "top_logprobs", "max_tokens", "max_completion_tokens", "n", "presence_penalty", "seed", "stop", "stream", "stream_options", "temperature", "top_p", "tools", "tool_choice", "function_call", "functions", "max_retries", "extra_headers", "parallel_tool_calls", "response_format" ] }, { "model_group": "llava-hf", "providers": [ "openai" ], "max_input_tokens": null, "max_output_tokens": null, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "mode": null, "tpm": null, "rpm": null, "supports_parallel_function_calling": false, "supports_vision": true, "supports_function_calling": false, "supported_openai_params": [ "frequency_penalty", "logit_bias", "logprobs", "top_logprobs", "max_tokens", "max_completion_tokens", "n", "presence_penalty", "seed", "stop", "stream", "stream_options", "temperature", "top_p", "tools", "tool_choice", "function_call", "functions", "max_retries", "extra_headers", "parallel_tool_calls", "response_format" ] } ] } ``` */
+export const getModelGroupInfoModelGroupInfo: API.OperationMethod<
+  GetModelGroupInfoModelGroupInfoRequest,
+  GetModelGroupInfoModelGroupInfoResponse,
+  GetModelGroupInfoModelGroupInfoError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelGroupInfoModelGroupInfoRequest,
+  output: GetModelGroupInfoModelGroupInfoResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelInfoModelsModelIdError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Info Retrieve information about a specific model accessible to your API key. Returns model details only if the model is available to your API key/team. Returns 404 if the model doesn't exist or is not accessible. Follows OpenAI API specification for individual model retrieval. https://platform.openai.com/docs/api-reference/models/retrieve Query parameters mirror `/v1/models` so the same caller context (team scoping, health filtering, paused deployments) drives both endpoints; the listing's public id must resolve to the same internal deployment here. */
+export const getModelInfoModelsModelId: API.OperationMethod<
+  GetModelInfoModelsModelIdRequest,
+  GetModelInfoModelsModelIdResponse,
+  GetModelInfoModelsModelIdError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelInfoModelsModelIdRequest,
+  output: GetModelInfoModelsModelIdResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelInfoV1ModelInfoError = UnprocessableEntity | LitellmOpError;
+/** Model Info V1 Provides more info about each model in /models, including config.yaml descriptions (except api key and api base) Parameters: litellm_model_id: Optional[str] = None (this is the value of `x-litellm-model-id` returned in response headers) - When litellm_model_id is passed, it will return the info for that specific model - When litellm_model_id is not passed, it will return the info for all models - include_team_models: When true, filter to deployments the caller can use (same as /v2/model/info). - teamId: Filter to models accessible by the given team. - healthy_only: When true, hide models whose backing deployments are all marked unhealthy by background health checks, matching `/v1/models?healthy_only=true`. Set `general_settings.model_list_healthy_only: true` to apply this to every caller without the query parameter. Requires `background_health_checks: true`, plus either `model_list_healthy_only` or `enable_health_check_routing` to keep deployment health state cached; without health state the listing is returned unfiltered (fail open). Ignored when `litellm_model_id` is passed, since that is a direct lookup of one deployment rather than a listing. Hiding is presentation-only: a hidden model can still be called directly. Each model in the list response includes `model_info.access_via_team_ids` and `model_info.direct_access` when the proxy database is connected. Returns: Returns a dictionary containing information about each model. Example Response: ```json { "data": [ { "model_name": "fake-openai-endpoint", "litellm_params": { "api_base": "https://exampleopenaiendpoint-production.up.railway.app/", "model": "openai/fake" }, "model_info": { "id": "112f74fab24a7a5245d2ced3536dd8f5f9192c57ee6e332af0f0512e08bed5af", "db_model": false } } ] } ``` */
+export const getModelInfoV1ModelInfo: API.OperationMethod<
+  GetModelInfoV1ModelInfoRequest,
+  GetModelInfoV1ModelInfoResponse,
+  GetModelInfoV1ModelInfoError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelInfoV1ModelInfoRequest,
+  output: GetModelInfoV1ModelInfoResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelInfoV1ModelsModelIdError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Info Retrieve information about a specific model accessible to your API key. Returns model details only if the model is available to your API key/team. Returns 404 if the model doesn't exist or is not accessible. Follows OpenAI API specification for individual model retrieval. https://platform.openai.com/docs/api-reference/models/retrieve Query parameters mirror `/v1/models` so the same caller context (team scoping, health filtering, paused deployments) drives both endpoints; the listing's public id must resolve to the same internal deployment here. */
+export const getModelInfoV1ModelsModelId: API.OperationMethod<
+  GetModelInfoV1ModelsModelIdRequest,
+  GetModelInfoV1ModelsModelIdResponse,
+  GetModelInfoV1ModelsModelIdError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelInfoV1ModelsModelIdRequest,
+  output: GetModelInfoV1ModelsModelIdResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelInfoV1V1ModelInfoError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Info V1 Provides more info about each model in /models, including config.yaml descriptions (except api key and api base) Parameters: litellm_model_id: Optional[str] = None (this is the value of `x-litellm-model-id` returned in response headers) - When litellm_model_id is passed, it will return the info for that specific model - When litellm_model_id is not passed, it will return the info for all models - include_team_models: When true, filter to deployments the caller can use (same as /v2/model/info). - teamId: Filter to models accessible by the given team. - healthy_only: When true, hide models whose backing deployments are all marked unhealthy by background health checks, matching `/v1/models?healthy_only=true`. Set `general_settings.model_list_healthy_only: true` to apply this to every caller without the query parameter. Requires `background_health_checks: true`, plus either `model_list_healthy_only` or `enable_health_check_routing` to keep deployment health state cached; without health state the listing is returned unfiltered (fail open). Ignored when `litellm_model_id` is passed, since that is a direct lookup of one deployment rather than a listing. Hiding is presentation-only: a hidden model can still be called directly. Each model in the list response includes `model_info.access_via_team_ids` and `model_info.direct_access` when the proxy database is connected. Returns: Returns a dictionary containing information about each model. Example Response: ```json { "data": [ { "model_name": "fake-openai-endpoint", "litellm_params": { "api_base": "https://exampleopenaiendpoint-production.up.railway.app/", "model": "openai/fake" }, "model_info": { "id": "112f74fab24a7a5245d2ced3536dd8f5f9192c57ee6e332af0f0512e08bed5af", "db_model": false } } ] } ``` */
+export const getModelInfoV1V1ModelInfo: API.OperationMethod<
+  GetModelInfoV1V1ModelInfoRequest,
+  GetModelInfoV1V1ModelInfoResponse,
+  GetModelInfoV1V1ModelInfoError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelInfoV1V1ModelInfoRequest,
+  output: GetModelInfoV1V1ModelInfoResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelInfoV2V2ModelInfoError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Info V2 Paginated model metadata for proxy deployments (pricing, provider, team access). Returns configured router deployments with enriched `model_info` (costs, provider, context window, etc.). Sensitive fields such as API keys and api_base are omitted. Query parameters: model: Filter to a single public `model_name`. user_models_only: When true, only return models created by the calling user. include_team_models: When true, populate `access_via_team_ids` and `direct_access` on each model and filter to deployments the caller can use. page / size: Pagination controls (defaults: page=1, size=50). search: Case-insensitive partial match on model name or team public name. modelId: Return a single deployment by LiteLLM model id. teamId: Filter to models with direct access or team membership for this team id. sortBy / sortOrder: Sort by model_name, created_at, updated_at, costs, or status. Example request: ``` curl -X GET 'http://localhost:4000/v2/model/info?include_team_models=true&page=1&size=50' \ --header 'Authorization: Bearer sk-1234' ``` Example response: ```json { "data": [ { "model_name": "gpt-4", "litellm_params": {"model": "openai/gpt-4.1"}, "model_info": { "id": "abc123", "litellm_provider": "openai", "access_via_team_ids": ["team-1"], "direct_access": true } } ], "total_count": 1, "current_page": 1, "total_pages": 1, "size": 50 } ``` */
+export const getModelInfoV2V2ModelInfo: API.OperationMethod<
+  GetModelInfoV2V2ModelInfoRequest,
+  GetModelInfoV2V2ModelInfoResponse,
+  GetModelInfoV2V2ModelInfoError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelInfoV2V2ModelInfoRequest,
+  output: GetModelInfoV2V2ModelInfoResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelMetricsExceptionsModelMetricsExceptionError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Metrics Exceptions View number of failed requests per model on config.yaml */
+export const getModelMetricsExceptionsModelMetricsException: API.OperationMethod<
+  GetModelMetricsExceptionsModelMetricsExceptionRequest,
+  GetModelMetricsExceptionsModelMetricsExceptionResponse,
+  GetModelMetricsExceptionsModelMetricsExceptionError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelMetricsExceptionsModelMetricsExceptionRequest,
+  output: GetModelMetricsExceptionsModelMetricsExceptionResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelMetricsModelMetricsError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Metrics View number of requests & avg latency per model on config.yaml */
+export const getModelMetricsModelMetrics: API.OperationMethod<
+  GetModelMetricsModelMetricsRequest,
+  GetModelMetricsModelMetricsResponse,
+  GetModelMetricsModelMetricsError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelMetricsModelMetricsRequest,
+  output: GetModelMetricsModelMetricsResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelMetricsSlowResponsesModelMetricsSlowResponseError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Metrics Slow Responses View number of hanging requests per model_group */
+export const getModelMetricsSlowResponsesModelMetricsSlowResponse: API.OperationMethod<
+  GetModelMetricsSlowResponsesModelMetricsSlowResponseRequest,
+  GetModelMetricsSlowResponsesModelMetricsSlowResponseResponse,
+  GetModelMetricsSlowResponsesModelMetricsSlowResponseError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelMetricsSlowResponsesModelMetricsSlowResponseRequest,
+  output: GetModelMetricsSlowResponsesModelMetricsSlowResponseResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelSettingsModelSettingsError = LitellmOpError;
+/** Model Settings Returns provider name, description, and required parameters for each provider */
+export const getModelSettingsModelSettings: API.OperationMethod<
+  GetModelSettingsModelSettingsRequest,
+  GetModelSettingsModelSettingsResponse,
+  GetModelSettingsModelSettingsError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelSettingsModelSettingsRequest,
+  output: GetModelSettingsModelSettingsResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type GetModelStreamingMetricsModelStreamingMetricsError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model Streaming Metrics View time to first token for models in spend logs */
+export const getModelStreamingMetricsModelStreamingMetrics: API.OperationMethod<
+  GetModelStreamingMetricsModelStreamingMetricsRequest,
+  GetModelStreamingMetricsModelStreamingMetricsResponse,
+  GetModelStreamingMetricsModelStreamingMetricsError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: GetModelStreamingMetricsModelStreamingMetricsRequest,
+  output: GetModelStreamingMetricsModelStreamingMetricsResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type ListAccessGroupsAccessGroupListGetError = LitellmOpError;
+/** List Access Groups List all access groups. Returns a list of all access groups with their model names, deployment counts, shared budget and the spend drawn against it. Example: ```bash curl -X GET 'http://localhost:4000/access_group/list' \ -H 'Authorization: Bearer sk-1234' ``` Returns: - ListAccessGroupsResponse with all access groups */
+export const listAccessGroupsAccessGroupListGet: API.OperationMethod<
+  ListAccessGroupsAccessGroupListGetRequest,
+  ListAccessGroupsResponse,
+  ListAccessGroupsAccessGroupListGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: ListAccessGroupsAccessGroupListGetRequest,
+  output: ListAccessGroupsResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type ModelListModelsGetError =
+  | BadRequest
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Model List Use `/model/info` - to get detailed model information, example - pricing, mode, etc. This is just for compatibility with openai projects like aider. Query Parameters: - include_metadata: Include additional metadata in the response with fallback information - fallback_type: Type of fallbacks to include ("general", "context_window", "content_policy") Defaults to "general" when include_metadata=true - scope: Optional scope parameter. Currently only accepts "expand". When scope=expand is passed, proxy admins, team admins, and org admins will receive all proxy models as if they are a proxy admin. - healthy_only: When true, hide models whose backing deployments are all marked unhealthy by background health checks. Set `general_settings.model_list_healthy_only: true` to apply this to every caller without the query parameter. Requires `background_health_checks: true` in general_settings, plus either `model_list_healthy_only` or `enable_health_check_routing` to keep deployment health state cached; without health state the listing is returned unfiltered (fail open). Models expanded from wildcard routes (e.g. `openai/*`) are not filtered, and nothing is hidden when `allowed_fails_policy` is configured (cooldown remains the sole exclusion mechanism). Hiding is presentation-only: a hidden model can still be called directly. */
+export const modelListModelsGet: API.OperationMethod<
+  ModelListModelsGetRequest,
+  ModelListModelsGetResponse,
+  ModelListModelsGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: ModelListModelsGetRequest,
+  output: ModelListModelsGetResponse,
+  errors: [BadRequest, UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type ModelListV1ModelsGetError = UnprocessableEntity | LitellmOpError;
+/** Model List Use `/model/info` - to get detailed model information, example - pricing, mode, etc. This is just for compatibility with openai projects like aider. Query Parameters: - include_metadata: Include additional metadata in the response with fallback information - fallback_type: Type of fallbacks to include ("general", "context_window", "content_policy") Defaults to "general" when include_metadata=true - scope: Optional scope parameter. Currently only accepts "expand". When scope=expand is passed, proxy admins, team admins, and org admins will receive all proxy models as if they are a proxy admin. - healthy_only: When true, hide models whose backing deployments are all marked unhealthy by background health checks. Set `general_settings.model_list_healthy_only: true` to apply this to every caller without the query parameter. Requires `background_health_checks: true` in general_settings, plus either `model_list_healthy_only` or `enable_health_check_routing` to keep deployment health state cached; without health state the listing is returned unfiltered (fail open). Models expanded from wildcard routes (e.g. `openai/*`) are not filtered, and nothing is hidden when `allowed_fails_policy` is configured (cooldown remains the sole exclusion mechanism). Hiding is presentation-only: a hidden model can still be called directly. */
+export const modelListV1ModelsGet: API.OperationMethod<
+  ModelListV1ModelsGetRequest,
+  ModelListV1ModelsGetResponse,
+  ModelListV1ModelsGetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: ModelListV1ModelsGetRequest,
+  output: ModelListV1ModelsGetResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PatchModelModelModelIdUpdatePatchError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Patch Model PATCH Endpoint for partial model updates. Only updates the fields specified in the request while preserving other existing values. Follows proper PATCH semantics by only modifying provided fields. Args: model_id: The ID of the model to update patch_data: The fields to update and their new values user_api_key_dict: User authentication information Returns: Updated model information Raises: ProxyException: For various error conditions including authentication and database errors */
+export const patchModelModelModelIdUpdatePatch: API.OperationMethod<
+  PatchModelModelModelIdUpdatePatchRequest,
+  PatchModelModelModelIdUpdatePatchResponse,
+  PatchModelModelModelIdUpdatePatchError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PatchModelModelModelIdUpdatePatchRequest,
+  output: PatchModelModelModelIdUpdatePatchResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostBlockModelModelBlockError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Block Model Block a DB-stored model deployment from serving requests. Parameters: - model_id: str - The model deployment id to block. */
+export const postBlockModelModelBlock: API.OperationMethod<
+  PostBlockModelModelBlockRequest,
+  PostBlockModelModelBlockResponse,
+  PostBlockModelModelBlockError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PostBlockModelModelBlockRequest,
+  output: PostBlockModelModelBlockResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Preview Auto Router Classifier Prompt Get the system prompt an auto-router's LLM classifier sends for an edited tier set */
+export const postPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPrompt: API.OperationMethod<
+  PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequest,
+  AutoRouterClassifierDefaultPromptResponse,
+  PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input:
+    PostPreviewAutoRouterClassifierPromptAutoRouterClassifierDefaultPromptRequest,
+  output: AutoRouterClassifierDefaultPromptResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostPreviewAutoRouterRoutingAutoRouterTestRoutingError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Preview Auto Router Routing Route a single request through a complexity-router config and report where it landed. Answers "which model would this request get?" for a config that only exists in a form, so an auto router can be checked before it is created. The request is classified by the same pre-routing hook a live request runs, over the same messages, system prompt and tool definitions, then dropped: nothing is sent to the model it routed to, and no auto router is created. A heuristic config therefore spends nothing, while an `llm` classifier or semantic keyword matching bills its classifier/embedding call to the calling key, like Test Connection does. Send `messages` to classify a real turn, with `system` and `tools` beside it when the surface carries them top level, as Anthropic /v1/messages does. `prompt` is the single-ask shorthand and routes as one user turn with nothing around it. **Example Request:** ```json { "messages": [ {"role": "system", "content": "You are a database migration assistant"}, {"role": "user", "content": "the index is not unique"}, {"role": "assistant", "content": "Then two workers can both insert. Add a unique index"}, {"role": "user", "content": "ok do it"} ], "tools": [{"type": "function", "function": {"name": "Bash", "description": "Run a command"}}], "complexity_router_config": { "tiers": {"SIMPLE": ["gpt-4o-mini"], "REASONING": ["o3"]}, "classifier_type": "heuristic" } } ``` */
+export const postPreviewAutoRouterRoutingAutoRouterTestRouting: API.OperationMethod<
+  PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequest,
+  AutoRouterRoutingTestResponse,
+  PostPreviewAutoRouterRoutingAutoRouterTestRoutingError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PostPreviewAutoRouterRoutingAutoRouterTestRoutingRequest,
+  output: AutoRouterRoutingTestResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderError =
+  LitellmOpError;
+/** Reload Anthropic Beta Headers ADMIN ONLY / MASTER KEY Only Endpoint Manually reload the Anthropic beta headers configuration from the remote source. This will fetch fresh configuration from the anthropic_beta_headers_config.json file. */
+export const postReloadAnthropicBetaHeadersReloadAnthropicBetaHeader: API.OperationMethod<
+  PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderRequest,
+  PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderResponse,
+  PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderRequest,
+  output: PostReloadAnthropicBetaHeadersReloadAnthropicBetaHeaderResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostReloadModelCostMapReloadModelCostMapError = LitellmOpError;
+/** Reload Model Cost Map ADMIN ONLY / MASTER KEY Only Endpoint Manually reload the model cost map from the remote source. This will fetch fresh pricing data from the model_prices_and_context_window.json file. */
+export const postReloadModelCostMapReloadModelCostMap: API.OperationMethod<
+  PostReloadModelCostMapReloadModelCostMapRequest,
+  PostReloadModelCostMapReloadModelCostMapResponse,
+  PostReloadModelCostMapReloadModelCostMapError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PostReloadModelCostMapReloadModelCostMapRequest,
+  output: PostReloadModelCostMapReloadModelCostMapResponse,
+  errors: [],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Schedule Anthropic Beta Headers Reload ADMIN ONLY / MASTER KEY Only Endpoint Schedule periodic reload of the Anthropic beta headers configuration. This will create a background job that reloads the configuration every specified hours. */
+export const postScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReload: API.OperationMethod<
+  PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadRequest,
+  PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadResponse,
+  PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input:
+    PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadRequest,
+  output:
+    PostScheduleAnthropicBetaHeadersReloadScheduleAnthropicBetaHeadersReloadResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PostScheduleModelCostMapReloadScheduleModelCostMapReloadError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Schedule Model Cost Map Reload ADMIN ONLY / MASTER KEY Only Endpoint Schedule periodic reload of the model cost map. This will create a background job that reloads the model cost map every specified hours. */
+export const postScheduleModelCostMapReloadScheduleModelCostMapReload: API.OperationMethod<
+  PostScheduleModelCostMapReloadScheduleModelCostMapReloadRequest,
+  PostScheduleModelCostMapReloadScheduleModelCostMapReloadResponse,
+  PostScheduleModelCostMapReloadScheduleModelCostMapReloadError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PostScheduleModelCostMapReloadScheduleModelCostMapReloadRequest,
+  output: PostScheduleModelCostMapReloadScheduleModelCostMapReloadResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Set Access Group Budget Set or replace the shared budget of an access group. Idempotent. Every key that can reach a model in the group draws from this one budget. Example: ```bash curl -X PUT 'http://localhost:4000/access_group/production-models/budget' \ -H 'Authorization: Bearer sk-1234' \ -H 'Content-Type: application/json' \ -d '{ "max_budget": 100.0, "budget_duration": "30d" }' ``` Parameters: - access_group: str - The access group name (URL path parameter) - max_budget: Optional[float] - Requests fail once the group's shared spend exceeds this - soft_budget: Optional[float] - Fires an alert when reached; requests still succeed - budget_duration: Optional[str] - Frequency of resetting the group's spend (e.g. '30d') - budget_id: Optional[str] - Link an existing budget instead of creating one Returns: - AccessGroupBudgetResponse with the stored budget and current spend Raises: - HTTPException 400: If no budget field is given, or budget_duration cannot be parsed - HTTPException 404: If access group not found */
+export const putSetAccessGroupBudgetAccessGroupAccessGroupBudget: API.OperationMethod<
+  PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetRequest,
+  AccessGroupBudgetResponse,
+  PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: PutSetAccessGroupBudgetAccessGroupAccessGroupBudgetRequest,
+  output: AccessGroupBudgetResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type UnblockModelModelUnblockPostError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Unblock Model Unblock a DB-stored model deployment so it can serve requests again. Parameters: - model_id: str - The model deployment id to unblock. */
+export const unblockModelModelUnblockPost: API.OperationMethod<
+  UnblockModelModelUnblockPostRequest,
+  UnblockModelModelUnblockPostResponse,
+  UnblockModelModelUnblockPostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: UnblockModelModelUnblockPostRequest,
+  output: UnblockModelModelUnblockPostResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type UpdateAccessGroupAccessGroupAccessGroupUpdatePutError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Update Access Group Update an access group's model names. This will: 1. Remove the access group from all current deployments 2. Add the access group to all deployments for the new model_names list Example: ```bash curl -X PUT 'http://localhost:4000/access_group/production-models/update' \ -H 'Authorization: Bearer sk-1234' \ -H 'Content-Type: application/json' \ -d '{ "model_names": ["gpt-4", "claude-3-sonnet"] }' ``` Parameters: - access_group: str - The access group name (URL path parameter) - model_names: List[str] - New list of model groups to include Returns: - NewModelGroupResponse with the updated access group details Raises: - HTTPException 400: If any model names don't exist - HTTPException 404: If access group not found */
+export const updateAccessGroupAccessGroupAccessGroupUpdatePut: API.OperationMethod<
+  UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequest,
+  NewModelGroupResponse,
+  UpdateAccessGroupAccessGroupAccessGroupUpdatePutError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: UpdateAccessGroupAccessGroupAccessGroupUpdatePutRequest,
+  output: NewModelGroupResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type UpdateModelModelUpdatePostError =
+  | BadRequest
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Update Model Edit existing model params */
+export const updateModelModelUpdatePost: API.OperationMethod<
+  UpdateModelModelUpdatePostRequest,
+  UpdateModelModelUpdatePostResponse,
+  UpdateModelModelUpdatePostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: UpdateModelModelUpdatePostRequest,
+  output: UpdateModelModelUpdatePostResponse,
+  errors: [BadRequest, UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type UpdatePublicModelGroupsModelGroupMakePublicPostError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Update Public Model Groups Update which model groups are public */
+export const updatePublicModelGroupsModelGroupMakePublicPost: API.OperationMethod<
+  UpdatePublicModelGroupsModelGroupMakePublicPostRequest,
+  UpdatePublicModelGroupsModelGroupMakePublicPostResponse,
+  UpdatePublicModelGroupsModelGroupMakePublicPostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: UpdatePublicModelGroupsModelGroupMakePublicPostRequest,
+  output: UpdatePublicModelGroupsModelGroupMakePublicPostResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type UpdateUsefulLinksModelHubUpdateUsefulLinksPostError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Update Useful Links Update useful links */
+export const updateUsefulLinksModelHubUpdateUsefulLinksPost: API.OperationMethod<
+  UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequest,
+  UpdateUsefulLinksModelHubUpdateUsefulLinksPostResponse,
+  UpdateUsefulLinksModelHubUpdateUsefulLinksPostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input: UpdateUsefulLinksModelHubUpdateUsefulLinksPostRequest,
+  output: UpdateUsefulLinksModelHubUpdateUsefulLinksPostResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));
+
+export type ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostError =
+  | UnprocessableEntity
+  | LitellmOpError;
+/** Validate Complexity Router Config Validate a complexity-router config without saving it. Runs the same check every write path runs (the router's own pydantic model), so a form can show the backend's exact verdict while the operator is still editing rather than after a rejected save. Gated exactly like the save it rehearses: a proxy admin, or a team admin naming their own team. Nothing is created, routed, or billed. */
+export const validateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPost: API.OperationMethod<
+  ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequest,
+  ComplexityRouterConfigValidationResponse,
+  ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostError,
+  LitellmOpContext
+> = /*@__PURE__*/ API.make(() => ({
+  input:
+    ValidateComplexityRouterConfigAutoRouterValidateComplexityRouterConfigPostRequest,
+  output: ComplexityRouterConfigValidationResponse,
+  errors: [UnprocessableEntity],
+  protocol: LitellmProtocol,
+  retry: Retry.Retry,
+}));