openrouter

type APIError struct {
	Code     any       `json:"code,omitempty"`
	Message  string    `json:"message"`
	Metadata *Metadata `json:"metadata,omitempty"`

	// Internal fields
	HTTPStatusCode int            `json:"-"`
	ProviderError  *ProviderError `json:"-"`
}

type APIKey struct {
	Hash               string        `json:"hash,omitempty"`
	Name               string        `json:"name,omitempty"`
	Label              string        `json:"label,omitempty"`
	Disabled           bool          `json:"disabled,omitempty"`
	Limit              float64       `json:"limit,omitempty"`
	LimitRemaining     float64       `json:"limit_remaining,omitempty"`
	LimitReset         KeyLimitReset `json:"limit_reset,omitempty"`
	IncludeByokInLimit bool          `json:"include_byok_in_limit,omitempty"`

	Usage        float64 `json:"usage,omitempty"`
	UsageDaily   float64 `json:"usage_daily,omitempty"`
	UsageWeekly  float64 `json:"usage_weekly,omitempty"`
	UsageMonthly float64 `json:"usage_monthly,omitempty"`

	ByokUsage        float64 `json:"byok_usage,omitempty"`
	ByokUsageDaily   float64 `json:"byok_usage_daily,omitempty"`
	ByokUsageWeekly  float64 `json:"byok_usage_weekly,omitempty"`
	ByokUsageMonthly float64 `json:"byok_usage_monthly,omitempty"`

	CreatedAt time.Time  `json:"created_at,omitempty"`
	UpdatedAt *time.Time `json:"updated_at,omitempty"`
	ExpiresAt *time.Time `json:"expires_at,omitempty"`
}

type APIKeyCreateRequest struct {
	Name               string        `json:"name,omitempty"`
	Limit              float64       `json:"limit,omitempty"`
	LimitReset         KeyLimitReset `json:"limit_reset,omitempty"`
	IncludeByokInLimit *bool         `json:"include_byok_in_limit,omitempty"`
	ExpiresAt          *time.Time    `json:"expires_at,omitempty"`
}

type APIKeyCreateResponse struct {
	Data APIKey `json:"data"`
	Key  string `json:"key,omitempty"`
}

type APIKeyCurrent struct {
	Label              string        `json:"label,omitempty"`
	Limit              float64       `json:"limit,omitempty"`
	Usage              float64       `json:"usage,omitempty"`
	UsageDaily         float64       `json:"usage_daily,omitempty"`
	UsageWeekly        float64       `json:"usage_weekly,omitempty"`
	UsageMonthly       float64       `json:"usage_monthly,omitempty"`
	ByokUsage          float64       `json:"byok_usage,omitempty"`
	ByokUsageDaily     float64       `json:"byok_usage_daily,omitempty"`
	ByokUsageWeekly    float64       `json:"byok_usage_weekly,omitempty"`
	ByokUsageMonthly   float64       `json:"byok_usage_monthly,omitempty"`
	IsFreeTier         bool          `json:"is_free_tier,omitempty"`
	IsProvisioningKey  bool          `json:"is_provisioning_key,omitempty"`
	LimitRemaining     float64       `json:"limit_remaining,omitempty"`
	LimitReset         KeyLimitReset `json:"limit_reset,omitempty"`
	IncludeByokInLimit bool          `json:"include_byok_in_limit,omitempty"`
	RateLimit          *APIRateLimit `json:"rate_limit,omitempty"`
	ExpiresAt          *time.Time    `json:"expires_at,omitempty"`
}

type APIKeyCurrentResponse struct {
	Data APIKeyCurrent `json:"data"`
}

type APIKeyDeleteResponse struct {
	Deleted bool `json:"deleted"`
}

type APIKeyResponse struct {
	Data APIKey `json:"data"`
}

type APIKeyUpdateRequest struct {
	Name               *string        `json:"name,omitempty"`
	Disabled           *bool          `json:"disabled,omitempty"`
	Limit              *float64       `json:"limit,omitempty"`
	LimitReset         *KeyLimitReset `json:"limit_reset,omitempty"`
	IncludeByokInLimit *bool          `json:"include_byok_in_limit,omitempty"`
	ExpiresAt          *time.Time     `json:"expires_at,omitempty"`
}

type APIKeysListResponse struct {
	Data []APIKey `json:"data"`
}

type APIRateLimit struct {
	Requests int    `json:"requests"`
	Interval string `json:"interval"`
	Note     string `json:"note,omitempty"`
}

type Annotation struct {
	Type        AnnotationType `json:"type"`
	URLCitation URLCitation    `json:"url_citation"`
}

type AnnotationType string

type AudioFormat string

type CacheControl struct {
	// Type only supports "ephemeral" for now.
	Type string `json:"type"`
	// TTL in  format of "5m" | "1h"
	TTL *string `json:"ttl,omitempty"`
}

type ChatCompletionAspectRatio string

type ChatCompletionChoice struct {
	Index            int                              `json:"index"`
	Message          ChatCompletionMessage            `json:"message"`
	Reasoning        *string                          `json:"reasoning,omitempty"`
	ReasoningDetails []ChatCompletionReasoningDetails `json:"reasoning_details,omitempty"`
	// FinishReason
	// stop: API returned complete message,
	// or a message terminated by one of the stop sequences provided via the stop parameter
	// length: Incomplete model output due to max_tokens parameter or token limit
	// function_call: The model decided to call a function
	// content_filter: Omitted content due to a flag from our content filters
	// null: API response still in progress or incomplete
	FinishReason       FinishReason `json:"finish_reason"`
	NativeFinishReason string       `json:"native_finish_reason"`
	LogProbs           *LogProbs    `json:"logprobs,omitempty"`
}

type ChatCompletionImage struct {
	Index    int                     `json:"index"`
	Type     ChatCompletionImageType `json:"type"`
	ImageURL ChatCompletionImageURL  `json:"image_url"`
}

type ChatCompletionImageConfig struct {
	AspectRatio ChatCompletionAspectRatio `json:"aspect_ratio,omitempty"`
	ImageSize   ChatCompletionImageSize   `json:"image_size,omitempty"`
}

type ChatCompletionImageSize string

type ChatCompletionImageType string

type ChatCompletionImageURL struct {
	URL string `json:"url"`
}

type ChatCompletionMessage struct {
	Role    string  `json:"role"`
	Content Content `json:"content,omitzero"`
	Refusal string  `json:"refusal,omitempty"`

	// This property is used for the "reasoning" feature supported by deepseek-reasoner
	// - https://api-docs.deepseek.com/api/create-chat-completion#responses
	ReasoningContent *string `json:"reasoning_content,omitempty"`

	// Reasoning Used by all the other models
	Reasoning *string `json:"reasoning,omitempty"`
	// Required to preserve reasoning blocks https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks
	ReasoningDetails []ChatCompletionReasoningDetails `json:"reasoning_details,omitempty"`

	FunctionCall *FunctionCall `json:"function_call,omitempty"`

	// For Role=assistant prompts this may be set to the tool calls generated by the model, such as function calls.
	ToolCalls []ToolCall `json:"tool_calls,omitempty"`

	// For Role=tool prompts this should be set to the ID given in the assistant's prior request to call a tool.
	ToolCallID string `json:"tool_call_id,omitempty"`

	// Web Search Annotations
	Annotations []Annotation `json:"annotations,omitempty"`

	// Multi-modal image generation (only in responses)
	Images []ChatCompletionImage `json:"images,omitempty"`
}

type ChatCompletionModality string

type ChatCompletionPlugin struct {
	ID         PluginID   `json:"id"`
	PDF        *PDFPlugin `json:"pdf,omitempty"`
	MaxResults *int       `json:"max_results,omitempty"`
}

type ChatCompletionReasoning struct {
	// Effort The prompt that was used to generate the reasoning. [high, medium, low]
	Effort *string `json:"prompt,omitempty"`

	// MaxTokens cannot be simultaneously used with effort.
	MaxTokens *int `json:"max_tokens,omitempty"`

	// Exclude defaults to false.
	Exclude *bool `json:"exclude,omitempty"`

	// Or enable reasoning with the default parameters:
	// Default: inferred from `effort` or `max_tokens`
	Enabled *bool `json:"enabled,omitempty"`
}

type ChatCompletionReasoningDetails struct {
	ID      string                             `json:"id,omitempty"`
	Index   int                                `json:"index"`
	Type    ChatCompletionReasoningDetailsType `json:"type"`
	Text    string                             `json:"text,omitempty"`
	Summary string                             `json:"summary,omitempty"`
	Data    string                             `json:"data,omitempty"`
	Format  string                             `json:"format,omitempty"`
}

type ChatCompletionReasoningDetailsType string

type ChatCompletionRequest struct {
	Model string `json:"model,omitempty"`
	// Optional model fallbacks: https://openrouter.ai/docs/features/model-routing#the-models-parameter
	Models   []string                `json:"models,omitempty"`
	Provider *ChatProvider           `json:"provider,omitempty"`
	Messages []ChatCompletionMessage `json:"messages"`

	Reasoning *ChatCompletionReasoning `json:"reasoning,omitempty"`

	Plugins    []ChatCompletionPlugin   `json:"plugins,omitempty"`
	Modalities []ChatCompletionModality `json:"modalities,omitempty"`

	ImageConfig *ChatCompletionImageConfig `json:"image_config,omitempty"`

	// MaxTokens The maximum number of tokens that can be generated in the chat completion.
	// This value can be used to control costs for text generated via API.
	MaxTokens int `json:"max_tokens,omitempty"`
	// MaxCompletionTokens Upper bound for completion tokens, supported for OpenAI API compliance.
	// Prefer "max_tokens" for limiting output in new integrations.
	// refs: https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_completion_tokens
	MaxCompletionTokens int                           `json:"max_completion_tokens,omitempty"`
	Temperature         float32                       `json:"temperature,omitempty"`
	TopP                float32                       `json:"top_p,omitempty"`
	TopK                int                           `json:"top_k,omitempty"`
	TopA                float32                       `json:"top_a,omitempty"`
	N                   int                           `json:"n,omitempty"`
	Stream              bool                          `json:"stream,omitempty"`
	Stop                []string                      `json:"stop,omitempty"`
	PresencePenalty     float32                       `json:"presence_penalty,omitempty"`
	RepetitionPenalty   float32                       `json:"repetition_penalty,omitempty"`
	ResponseFormat      *ChatCompletionResponseFormat `json:"response_format,omitempty"`
	Seed                *int                          `json:"seed,omitempty"`
	MinP                float32                       `json:"min_p,omitempty"`
	FrequencyPenalty    float32                       `json:"frequency_penalty,omitempty"`
	// LogitBias is must be a token id string (specified by their token ID in the tokenizer), not a word string.
	// incorrect: `"logit_bias":{"You": 6}`, correct: `"logit_bias":{"1639": 6}`
	// refs: https://platform.openai.com/docs/api-reference/chat/create#chat/create-logit_bias
	LogitBias map[string]int `json:"logit_bias,omitempty"`
	// LogProbs indicates whether to return log probabilities of the output tokens or not.
	// If true, returns the log probabilities of each output token returned in the content of message.
	// This option is currently not available on the gpt-4-vision-preview model.
	LogProbs bool `json:"logprobs,omitempty"`
	// TopLogProbs is an integer between 0 and 5 specifying the number of most likely tokens to return at each
	// token position, each with an associated log probability.
	// logprobs must be set to true if this parameter is used.
	TopLogProbs int    `json:"top_logprobs,omitempty"`
	User        string `json:"user,omitempty"`
	// For usage with the broadcast feature. Group related requests together (such as a conversation or agent workflow) by including the session_id field (up to 128 characters).
	// https://openrouter.ai/docs/guides/features/broadcast/overview#optional-trace-data
	SessionId string `json:"session_id,omitempty"`
	// Deprecated: use Tools instead.
	Functions []FunctionDefinition `json:"functions,omitempty"`
	// Deprecated: use ToolChoice instead.
	FunctionCall any    `json:"function_call,omitempty"`
	Tools        []Tool `json:"tools,omitempty"`
	// This can be either a string or an ToolChoice object.
	ToolChoice any `json:"tool_choice,omitempty"`
	// Options for streaming response. Only set this when you set stream: true.
	StreamOptions *StreamOptions `json:"stream_options,omitempty"`
	// Disable the default behavior of parallel tool calls by setting it: false.
	ParallelToolCalls any `json:"parallel_tool_calls,omitempty"`
	// Store can be set to true to store the output of this completion request for use in distillations and evals.
	// https://platform.openai.com/docs/api-reference/chat/create#chat-create-store
	Store bool `json:"store,omitempty"`
	// Metadata to store with the completion.
	Metadata map[string]string `json:"metadata,omitempty"`
	// Trace provides structured tracing metadata for observability integrations.
	// https://openrouter.ai/docs/guides/features/broadcast/overview#custom-metadata
	Trace *ChatCompletionTrace `json:"trace,omitempty"`
	// Apply message transforms
	// https://openrouter.ai/docs/features/message-transforms
	Transforms []string `json:"transforms,omitempty"`
	// Optional web search options
	// https://openrouter.ai/docs/features/web-search#specifying-search-context-size
	WebSearchOptions *WebSearchOptions `json:"web_search_options,omitempty"`

	Usage *IncludeUsage `json:"usage,omitempty"`
}

type ChatCompletionResponse struct {
	ID                string                 `json:"id"`
	Object            string                 `json:"object"`
	Created           int64                  `json:"created"`
	Model             string                 `json:"model"`
	Provider          string                 `json:"provider"`
	Choices           []ChatCompletionChoice `json:"choices"`
	Citations         []string               `json:"citations"`
	Usage             *Usage                 `json:"usage,omitempty"`
	SystemFingerprint string                 `json:"system_fingerprint"`
}

type ChatCompletionResponseFormat struct {
	Type       ChatCompletionResponseFormatType        `json:"type,omitempty"`
	JSONSchema *ChatCompletionResponseFormatJSONSchema `json:"json_schema,omitempty"`
}

type ChatCompletionResponseFormatJSONSchema struct {
	Name        string         `json:"name"`
	Description string         `json:"description,omitempty"`
	Schema      json.Marshaler `json:"schema"`
	Strict      bool           `json:"strict"`
}

type ChatCompletionResponseFormatType string

type ChatCompletionStream struct {
	// contains filtered or unexported fields
}

type ChatCompletionStreamChoice struct {
	Index                int                                 `json:"index"`
	Delta                ChatCompletionStreamChoiceDelta     `json:"delta"`
	Logprobs             *ChatCompletionStreamChoiceLogprobs `json:"logprobs,omitempty"`
	FinishReason         FinishReason                        `json:"finish_reason"`
	NativeFinishReason   string                              `json:"native_finish_reason"`
	ContentFilterResults *ContentFilterResults               `json:"content_filter_results,omitempty"`
}

type ChatCompletionStreamChoiceDelta struct {
	Content          string                           `json:"content,omitempty"`
	Role             string                           `json:"role,omitempty"`
	FunctionCall     *FunctionCall                    `json:"function_call,omitempty"`
	ToolCalls        []ToolCall                       `json:"tool_calls,omitempty"`
	Refusal          string                           `json:"refusal,omitempty"`
	Annotations      []Annotation                     `json:"annotations,omitempty"`
	Images           []ChatCompletionImage            `json:"images,omitempty"`
	Reasoning        *string                          `json:"reasoning,omitempty"`
	ReasoningDetails []ChatCompletionReasoningDetails `json:"reasoning_details,omitempty"`

	// This property is used for the "reasoning" feature supported by deepseek-reasoner
	// which is not in the official documentation.
	// the doc from deepseek:
	// - https://api-docs.deepseek.com/api/create-chat-completion#responses
	ReasoningContent string `json:"reasoning_content,omitempty"`
}

type ChatCompletionStreamChoiceLogprobs struct {
	Content []ChatCompletionTokenLogprob `json:"content,omitempty"`
	Refusal []ChatCompletionTokenLogprob `json:"refusal,omitempty"`
}

type ChatCompletionStreamResponse struct {
	ID                  string                       `json:"id"`
	Object              string                       `json:"object"`
	Created             int64                        `json:"created"`
	Model               string                       `json:"model"`
	Provider            string                       `json:"provider"`
	Choices             []ChatCompletionStreamChoice `json:"choices"`
	SystemFingerprint   string                       `json:"system_fingerprint"`
	PromptAnnotations   []PromptAnnotation           `json:"prompt_annotations,omitempty"`
	PromptFilterResults []PromptFilterResult         `json:"prompt_filter_results,omitempty"`
	// An optional field that will only be present when you set stream_options: {"include_usage": true} in your request.
	// When present, it contains a null value except for the last chunk which contains the token usage statistics
	// for the entire request.
	Usage *Usage `json:"usage,omitempty"`
}

type ChatCompletionTokenLogprob struct {
	Token       string                                 `json:"token"`
	Bytes       []int64                                `json:"bytes,omitempty"`
	Logprob     float64                                `json:"logprob,omitempty"`
	TopLogprobs []ChatCompletionTokenLogprobTopLogprob `json:"top_logprobs"`
}

type ChatCompletionTokenLogprobTopLogprob struct {
	Token   string  `json:"token"`
	Bytes   []int64 `json:"bytes"`
	Logprob float64 `json:"logprob"`
}

type ChatCompletionTrace struct {
	// TraceID groups multiple API requests into a single trace.
	TraceID string `json:"trace_id,omitempty"`
	// TraceName is a custom identifier for the root trace; defaults to the model name.
	TraceName string `json:"trace_name,omitempty"`
	// SpanName creates a parent span that groups LLM operations.
	SpanName string `json:"span_name,omitempty"`
	// GenerationName is a custom identifier for this specific LLM call.
	GenerationName string `json:"generation_name,omitempty"`
	// ParentSpanID links this trace to an existing span in your own tracing system (e.g. OpenTelemetry).
	ParentSpanID string `json:"parent_span_id,omitempty"`
}

type ChatMessageImageURL struct {
	URL    string         `json:"url,omitempty"`
	Detail ImageURLDetail `json:"detail,omitempty"`
}

type ChatMessageInputAudio struct {
	Data   string      `json:"data,omitempty"`
	Format AudioFormat `json:"format,omitempty"`
}

type ChatMessagePart struct {
	Type ChatMessagePartType `json:"type,omitempty"`
	Text string              `json:"text,omitempty"`
	// Prompt caching
	// https://openrouter.ai/docs/features/prompt-caching
	CacheControl *CacheControl `json:"cache_control,omitempty"`

	ImageURL   *ChatMessageImageURL   `json:"image_url,omitempty"`
	InputAudio *ChatMessageInputAudio `json:"input_audio,omitempty"`
	File       *FileContent           `json:"file,omitempty"`
}

type ChatMessagePartType string

type ChatProvider struct {
	// The order of the providers in the list determines the order in which they are called.
	Order []string `json:"order,omitempty"`
	// Allow fallbacks to other providers if the primary provider fails. Default: true
	AllowFallbacks *bool `json:"allow_fallbacks,omitempty"`
	// Only use providers that support all parameters in your request.
	RequireParameters bool `json:"require_parameters,omitempty"`
	// Control whether to use providers that may store data.
	DataCollection DataCollection `json:"data_collection,omitempty"`
	// List of provider slugs to allow for this request.
	Only []string `json:"only,omitempty"`
	// List of provider slugs to skip for this request.
	Ignore []string `json:"ignore,omitempty"`
	// List of quantization levels to filter by (e.g. ["int4", "int8"]).
	Quantizations []string `json:"quantizations,omitempty"`
	// Sort providers by price or throughput. (e.g. "price" or "throughput").
	Sort ProviderSorting `json:"sort,omitempty"`
}

type Client struct {
	// contains filtered or unexported fields
}

type ClientConfig struct {
	BaseURL          string
	OrgID            string
	AssistantVersion string
	HTTPClient       HTTPDoer
	HttpReferer      string
	XTitle           string

	EmptyMessagesLimit uint
	// contains filtered or unexported fields
}

type CompletionChoice struct {
	Index int    `json:"index"`
	Text  string `json:"text"`
	// Reasoning Used by all the other models
	Reasoning *string `json:"reasoning,omitempty"`
	// FinishReason
	// stop: API returned complete message,
	// or a message terminated by one of the stop sequences provided via the stop parameter
	// length: Incomplete model output due to max_tokens parameter or token limit
	// function_call: The model decided to call a function
	// content_filter: Omitted content due to a flag from our content filters
	// null: API response still in progress or incomplete
	FinishReason FinishReason `json:"finish_reason"`
	LogProbs     *LogProbs    `json:"logprobs,omitempty"`
}

type CompletionRequest struct {
	Model string `json:"model,omitempty"`
	// The prompt to complete
	Prompt string `json:"prompt"`
	// Optional model fallbacks: https://openrouter.ai/docs/features/model-routing#the-models-parameter
	Models    []string                 `json:"models,omitempty"`
	Provider  *ChatProvider            `json:"provider,omitempty"`
	Reasoning *ChatCompletionReasoning `json:"reasoning,omitempty"`
	Usage     *IncludeUsage            `json:"usage,omitempty"`
	// Apply message transforms
	// https://openrouter.ai/docs/features/message-transforms
	Transforms []string `json:"transforms,omitempty"`
	Stream     bool     `json:"stream,omitempty"`
	// MaxTokens The maximum number of tokens that can be generated in the chat completion.
	// This value can be used to control costs for text generated via API.
	MaxTokens         int     `json:"max_tokens,omitempty"`
	Temperature       float32 `json:"temperature,omitempty"`
	Seed              *int    `json:"seed,omitempty"`
	TopP              float32 `json:"top_p,omitempty"`
	TopK              int     `json:"top_k,omitempty"`
	FrequencyPenalty  float32 `json:"frequency_penalty,omitempty"`
	PresencePenalty   float32 `json:"presence_penalty,omitempty"`
	RepetitionPenalty float32 `json:"repetition_penalty,omitempty"`
	// LogitBias is must be a token id string (specified by their token ID in the tokenizer), not a word string.
	// incorrect: `"logit_bias":{"You": 6}`, correct: `"logit_bias":{"1639": 6}`
	// refs: https://platform.openai.com/docs/api-reference/chat/create#chat/create-logit_bias
	LogitBias   map[string]int `json:"logit_bias,omitempty"`
	TopLogProbs int            `json:"top_logprobs,omitempty"`
	MinP        float32        `json:"min_p,omitempty"`
	TopA        float32        `json:"top_a,omitempty"`
	User        string         `json:"user,omitempty"`
	// For usage with the broadcast feature. Group related requests together (such as a conversation or agent workflow) by including the session_id field (up to 128 characters).
	// https://openrouter.ai/docs/guides/features/broadcast/overview#optional-trace-data
	SessionId string `json:"session_id,omitempty"`
}

type CompletionResponse struct {
	ID                string             `json:"id"`
	Object            string             `json:"object"`
	Created           int64              `json:"created"`
	Model             string             `json:"model"`
	Choices           []CompletionChoice `json:"choices"`
	Citations         []string           `json:"citations"`
	Usage             *Usage             `json:"usage,omitempty"`
	SystemFingerprint string             `json:"system_fingerprint"`
}

type CompletionStream struct {
	// contains filtered or unexported fields
}

type CompletionTokenDetails struct {
	ReasoningTokens int `json:"reasoning_tokens"`
	ImageTokens     int `json:"image_tokens"`
}

type Content struct {
	Text  string
	Multi []ChatMessagePart
}

type ContentFilterResults struct {
	Hate      Hate      `json:"hate,omitempty"`
	SelfHarm  SelfHarm  `json:"self_harm,omitempty"`
	Sexual    Sexual    `json:"sexual,omitempty"`
	Violence  Violence  `json:"violence,omitempty"`
	JailBreak JailBreak `json:"jailbreak,omitempty"`
	Profanity Profanity `json:"profanity,omitempty"`
}

type CostDetails struct {
	UpstreamInferenceCost           float64 `json:"upstream_inference_cost"`
	UpstreamInferencePromptCost     float64 `json:"upstream_inference_prompt_cost"`
	UpstreamInferenceCompletionCost float64 `json:"upstream_inference_completion_cost"`
}

type DataCollection string

type EmbeddingData struct {
	Object    string         `json:"object"`
	Embedding EmbeddingValue `json:"embedding"`
	Index     int            `json:"index"`
}

type EmbeddingValue struct {
	Vector []float64
	Base64 string
}

type EmbeddingsEncodingFormat string

type EmbeddingsRequest struct {
	// Model is the model slug to use for embeddings.
	Model string `json:"model"`
	// Input is the content to embed. See the API docs for supported formats.
	Input any `json:"input"`

	// EncodingFormat controls how the embedding is returned: "float" or "base64".
	EncodingFormat EmbeddingsEncodingFormat `json:"encoding_format,omitempty"`
	// Dimensions optionally truncates the embedding to the given number of dimensions.
	Dimensions *int `json:"dimensions,omitempty"`
	// User is an optional identifier for the end-user making the request.
	User string `json:"user,omitempty"`
	// Provider configuration for provider routing. This reuses the same structure
	// as chat/completions provider routing, which is compatible with the embeddings API.
	Provider *ChatProvider `json:"provider,omitempty"`
	// InputType is an optional hint describing the type of input, e.g. "text" or "image".
	InputType string `json:"input_type,omitempty"`
}

type EmbeddingsResponse struct {
	ID     string           `json:"id"`
	Object string           `json:"object"`
	Data   []EmbeddingData  `json:"data"`
	Model  string           `json:"model"`
	Usage  *EmbeddingsUsage `json:"usage,omitempty"`
}

type EmbeddingsUsage struct {
	PromptTokens int     `json:"prompt_tokens"`
	TotalTokens  int     `json:"total_tokens"`
	Cost         float64 `json:"cost"`
}

type ErrorResponse struct {
	Error *APIError `json:"error,omitempty"`
}

type FileContent struct {
	Filename string `json:"filename"`
	FileData string `json:"file_data"`
}

type FinishReason string

type FunctionCall struct {
	Name string `json:"name,omitempty"`
	// call function with arguments in JSON format
	Arguments string `json:"arguments,omitempty"`
}

type FunctionDefinition struct {
	Name        string `json:"name"`
	Description string `json:"description,omitempty"`
	Strict      bool   `json:"strict,omitempty"`
	// Parameters is an object describing the function.
	// You can pass json.RawMessage to describe the schema,
	// or you can pass in a struct which serializes to the proper JSON schema.
	// The jsonschema package is provided for convenience, but you should
	// consider another specialized library if you require more complex schemas.
	Parameters any `json:"parameters"`
}

type Generation struct {
	ID                     string   `json:"id"`
	TotalCost              float64  `json:"total_cost"`
	CreatedAt              string   `json:"created_at"`
	Model                  string   `json:"model"`
	Origin                 string   `json:"origin"`
	Usage                  float64  `json:"usage"`
	IsBYOK                 bool     `json:"is_byok"`
	UpstreamID             *string  `json:"upstream_id,omitempty"`
	CacheDiscount          *float64 `json:"cache_discount,omitempty"`
	UpstreamInferenceCost  *float64 `json:"upstream_inference_cost,omitempty"`
	AppID                  *int     `json:"app_id,omitempty"`
	Streamed               *bool    `json:"streamed,omitempty"`
	Cancelled              *bool    `json:"cancelled,omitempty"`
	ProviderName           *string  `json:"provider_name,omitempty"`
	Latency                *int     `json:"latency,omitempty"`
	ModerationLatency      *int     `json:"moderation_latency,omitempty"`
	GenerationTime         *int     `json:"generation_time,omitempty"`
	FinishReason           *string  `json:"finish_reason,omitempty"`
	NativeFinishReason     *string  `json:"native_finish_reason,omitempty"`
	TokensPrompt           *int     `json:"tokens_prompt,omitempty"`
	TokensCompletion       *int     `json:"tokens_completion,omitempty"`
	NativeTokensPrompt     *int     `json:"native_tokens_prompt,omitempty"`
	NativeTokensCompletion *int     `json:"native_tokens_completion,omitempty"`
	NativeTokensReasoning  *int     `json:"native_tokens_reasoning,omitempty"`
	NumMediaPrompt         *int     `json:"num_media_prompt,omitempty"`
	NumMediaCompletion     *int     `json:"num_media_completion,omitempty"`
	NumSearchResults       *int     `json:"num_search_results,omitempty"`
}

type HTTPDoer interface {
	Do(req *http.Request) (*http.Response, error)
}

type HTTPRequestBuilder struct {
	// contains filtered or unexported fields
}

type Hate struct {
	Filtered bool   `json:"filtered"`
	Severity string `json:"severity,omitempty"`
}

type ImageURLDetail string

type IncludeUsage struct {
	Include bool `json:"include"`
}

type JSONMarshaller struct{}

type JailBreak struct {
	Filtered bool `json:"filtered"`
	Detected bool `json:"detected"`
}

type KeyLimitReset string

type LogProb struct {
	Token   string  `json:"token"`
	LogProb float64 `json:"logprob"`
	Bytes   []byte  `json:"bytes,omitempty"` // Omitting the field if it is null
	// TopLogProbs is a list of the most likely tokens and their log probability, at this token position.
	// In rare cases, there may be fewer than the number of requested top_logprobs returned.
	TopLogProbs []TopLogProbs `json:"top_logprobs"`
}

type LogProbs struct {
	// Content is a list of message content tokens with log probability information.
	Content []LogProb `json:"content"`
}

type Marshaller interface {
	Marshal(value any) ([]byte, error)
}

type Metadata map[string]any

type Model struct {
	ID                  string            `json:"id"`
	Name                string            `json:"name"`
	Created             int64             `json:"created"`
	Description         string            `json:"description"`
	Architecture        ModelArchitecture `json:"architecture"`
	TopProvider         ModelTopProvider  `json:"top_provider"`
	Pricing             ModelPricing      `json:"pricing"`
	CanonicalSlug       *string           `json:"canonical_slug,omitempty"`
	ContextLength       *int64            `json:"context_length,omitempty"`
	HuggingFaceID       *string           `json:"hugging_face_id,omitempty"`
	PerRequestLimits    any               `json:"per_request_limits,omitempty"`
	SupportedParameters []string          `json:"supported_parameters,omitempty"`
}

type ModelArchitecture struct {
	InputModalities  []string `json:"input_modalities"`
	OutputModalities []string `json:"output_modalities"`
	Tokenizer        string   `json:"tokenizer"`
	InstructType     *string  `json:"instruct_type,omitempty"`
}

type ModelPricing struct {
	Prompt            string  `json:"prompt"`
	Completion        string  `json:"completion"`
	Image             string  `json:"image"`
	Request           string  `json:"request"`
	WebSearch         string  `json:"web_search"`
	InternalReasoning string  `json:"internal_reasoning"`
	InputCacheRead    *string `json:"input_cache_read,omitempty"`
	InputCacheWrite   *string `json:"input_cache_write,omitempty"`
}

type ModelTopProvider struct {
	IsModerated         bool   `json:"is_moderated"`
	ContextLength       *int64 `json:"context_length,omitempty"`
	MaxCompletionTokens *int64 `json:"max_completion_tokens,omitempty"`
}

type Option func(*ClientConfig)

type PDFEngine string

type PDFPlugin struct {
	Engine string `json:"engine"`
}

type PluginID string

type Profanity struct {
	Filtered bool `json:"filtered"`
	Detected bool `json:"detected"`
}

type PromptAnnotation struct {
	PromptIndex          int                  `json:"prompt_index,omitempty"`
	ContentFilterResults ContentFilterResults `json:"content_filter_results,omitempty"`
}

type PromptFilterResult struct {
	Index                int                  `json:"index"`
	ContentFilterResults ContentFilterResults `json:"content_filter_results,omitempty"`
}

type PromptTokenDetails struct {
	CachedTokens     int `json:"cached_tokens"`
	CacheWriteTokens int `json:"cache_write_tokens"`
	AudioTokens      int `json:"audio_tokens"`
	VideoTokens      int `json:"video_tokens"`
}

type ProviderError map[string]any

type ProviderSorting string

type RequestBuilder interface {
	Build(ctx context.Context, method, url string, body any, header http.Header) (*http.Request, error)
}

type RequestError struct {
	HTTPStatus     string
	HTTPStatusCode int
	Err            error
	Body           []byte
}

type SearchContextSize string

type SelfHarm struct {
	Filtered bool   `json:"filtered"`
	Severity string `json:"severity,omitempty"`
}

type Sexual struct {
	Filtered bool   `json:"filtered"`
	Severity string `json:"severity,omitempty"`
}

type StreamOptions struct {
	// If set, an additional chunk will be streamed before the data: [DONE] message.
	// The usage field on this chunk shows the token usage statistics for the entire request,
	// and the choices field will always be an empty array.
	// All other chunks will also include a usage field, but with a null value.
	IncludeUsage bool `json:"include_usage,omitempty"`
}

type Tool struct {
	Type     ToolType            `json:"type"`
	Function *FunctionDefinition `json:"function,omitempty"`
}

type ToolCall struct {
	// Index is not nil only in chat completion chunk object
	Index    *int         `json:"index,omitempty"`
	ID       string       `json:"id,omitempty"`
	Type     ToolType     `json:"type"`
	Function FunctionCall `json:"function"`
}

type ToolType string

type TopLogProbs struct {
	Token   string  `json:"token"`
	LogProb float64 `json:"logprob"`
	Bytes   []byte  `json:"bytes,omitempty"`
}

type URLCitation struct {
	StartIndex int    `json:"start_index"`
	EndIndex   int    `json:"end_index"`
	Title      string `json:"title"`
	Content    string `json:"content"`
	URL        string `json:"url"`
}

type Usage struct {
	PromptTokens           int                    `json:"prompt_tokens"`
	CompletionTokens       int                    `json:"completion_tokens"`
	CompletionTokenDetails CompletionTokenDetails `json:"completion_token_details"`
	TotalTokens            int                    `json:"total_tokens"`
	IsBYOK                 bool                   `json:"is_byok"`

	Cost        float64     `json:"cost"`
	CostDetails CostDetails `json:"cost_details"`

	PromptTokenDetails PromptTokenDetails `json:"prompt_token_details"`
}

type Violence struct {
	Filtered bool   `json:"filtered"`
	Severity string `json:"severity,omitempty"`
}

type WebSearchOptions struct {
	SearchContextSize SearchContextSize `json:"search_context_size"`
}