Namespace Glitch9.AIDevKit

Classes

AIClientException

Base exception class for all AI client-related errors. All exceptions thrown by AI client operations derive from this class.

AIClientSettings

Base class for AI client settings. This class is used to store API keys and other settings related to AI clients.

AIDevKitManager

Exposed central hub for AIDevKit for customization and user context.

AIDevKitUtility

Exposed utility class for AIDevKit for general helper methods and extensions.

Upload a file that can be used across various endpoints. The size of all the files uploaded by one organization can be up to 100 GB. The size of individual files can be a maximum of 512 MB or 2 million tokens for Assistants. See the Assistants Tools guide to learn more about the types of files supported. The Fine-tuning API only supports .jsonl files.

Please contact us if you need to increase these storage limits. https://help.openai.com/en/

AIProviderException

AIResourceBase

AIResourceCatalogBase<TDatabase, TResource, TSelf>

AllowedTools

AmazonTitanImageEditOptions

AmazonTitanImageOptions

AmazonTitanImageOptionsBase

AmazonTypes

Amazon Bedrock specific types.

AmazonTypes.S3Location

A storage location in an Amazon S3 bucket.

Annotation

AnnotationEnvelope

Non-flattened wrapper for different types of annotations.

ApiPolicy

ApiPopupAttribute

ApiRefAttribute

ApiSpecificAttribute

ApiSpecificPropertyAttribute

ApiUtility

ApproximateLocation

AudioBufferStateChangeEvent

Event raised when the state of an audio buffer changes.

AudioContentData

AudioIsolationRequest

AudioIsolationSettings

AudioPart

AudioPrice

Represents per-second audio pricing, used for text-to-speech and voice change models.

AudioPrompt

A specialized prompt for various audio-related requests, such as voice change, audio isolation, etc.
This class is used to pass the instruction and the audio to the respective audio model for processing.

AudioPurpose

AudioUsage

BaseApiPropertyAttribute

BaseModelInfo

Holds identifying information about the base model that a fine-tuned model was derived from. Used to trace the lineage of custom models back to their original foundation model.

ChatChoice

Represents the final aggregated result of a streaming chat completion from an LLM. This is not the raw 'ChatCompletionChoice' from provider APIs, but a unified domain model that accumulates and structures the complete response after streaming is finished. Returned as Generated<ChatChoice> from various chat APIs across different providers.

ChatCompletionExtensions

ChatCompletionRequest

Request for generating chat completions from an LLM model.

ChatCompletionRequestBase<TSelf, TInput, TAsset>

ChatState

ClickAction

CodeGenerationRequest

Added new on 2025.05.28 Request for generating code snippets or scripts for Unity C#.

CodeInterpreter

A tool that runs Python code to help generate a response to a prompt.

CodeInterpreter.FileIdSet

Code interpreter container.

CodeInterpreterOutput

A tool call to run code.

CodeInterpreterOutputImage

CodeInterpreterOutputLogs

CodeInterpreterResult

Be careful. This is not a separate tool call, but a sub-object used within CodeInterpreterCall.

CodeInterpreterSettings

CollectionExtensions

Extension methods for AIDevKit types.

ComparisonFilter

A filter used to compare a specified attribute key to a given value using a defined comparison operation.

CompoundFilter

Combine multiple filters using and or or.

ComputerAction

ComputerUse

A tool that controls a virtual computer.

ComputerUseCall

A tool call to a computer use tool. See the computer use guide for more information.

ComputerUseOutput

The output of a computer tool call.

ComputerUseSafetyCheck

ComputerUseScreenshotInfo

ContainerFileCitation

ContentPart

Base class for different types of content parts in a message. Each content part has a defined type, such as Text, Image(Url/Base64/FileId), Audio(Base64), or File(Base64/FileId).

ContentPart<T>

Base class for different types of content parts in a message. Each content part has a defined type, such as Text, Image(Url/Base64/FileId), Audio(Base64), or File(Base64/FileId).

ContextSizeExceededException

ConversationItem

ConversationItemExtensions

ConversationItemType

CountTokensRequest

CustomTool

A custom tool that processes input using a specified format.

CustomToolCall

A call to a custom tool created by the model.

CustomToolChoice

CustomToolDefinition

CustomToolFormat

Polymorphic format for custom tool input.

CustomToolFormatConverter

Polymorphic converter for CustomToolFormat.

CustomToolOutput

The output of a custom tool call from your code, being sent back to the model.

DefaultEmbeddingService

DefaultImageGenerationService

DefaultModels

DefaultSpeechToTextService

DefaultTextToSpeechService

DefaultVoices

DeleteFileRequest

DeleteModelRequest

DeleteVoiceRequest

DeltaText

Specialized text container for accumulating delta text.

DeltaTextState

DetokenizationRequest

DocumentContentData

DocumentPart

DomainPropertyAttribute

DoubleClickAction

DownloadFileRequest

DragAction

DragAction.Coordinate

ElevenLabsAudioOptions

Provider-specific audio options for ElevenLabs requests. Pass this via SetSpecificOptions() or the SetElevenLabsFormat() convenience method.

ElevenLabsMusicOptions

ElevenLabs-specific options for music generation requests.

ElevenLabsTypes

Types only used by ElevenLabs API.
This shit is here instead of the ElevenLabs assembly because this is used by GENTask and the UnityEditor Generator Windows.

Embedding

Represents an embedding output as an asset structure, designed to be used with Generated<Embedding>. This wrapper class allows for future extensibility, supporting not only float[] but also other embedding types as required by different APIs.

EmbeddingPrompt

EmbeddingRequest

EmbeddingsSettings

EmptyResponseException

FieldRefAttribute

FileCitation

FileContentData

FilePart

FilePathAnnotation

FilePrompt

FileRequest<TSelf, TResult>

FileSearch

A tool that searches for relevant content from uploaded files.

FileSearch.RankingOptions

Ranking options for search.

FileSearchOutput

FileSearchResult

FileSearchSettings

FileSource

FileSourceConversionExtensions

FindAction

FineTunedModel

Represents a fine-tuned (custom-trained) AI model. Extends Model with fine-tuned-specific semantics; IsFineTuned always returns true for instances of this class.

FineTunedModelCatalog

ScriptableObject database for storing fine-tuned (custom-trained) model assets. Mirrors ModelCatalog but is typed to FineTunedModel.

FineTunedModelCatalog.Repo

Database for storing fine-tuned model data.

FineTuningFile

A JSONL file is a text file where each line is a valid JSON object. This format is commonly used for training data in machine learning tasks, including fine-tuning.

FineTuningRequest

FreePrice

Represents a free pricing tier with zero cost.

FrequencyPenalty

Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Function

Structured representation of a function declaration as defined by the OpenAPI 3.03 specification. Included in this declaration are the function name and parameters. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.

FunctionCall

A tool call to run a function. See the function calling guide for more information.

FunctionOutput

The output of a function tool call.

FunctionPropertyAttribute

Attribute for marking properties as function parameters in JSON Schema for LLM function calls.

Note: It's a duplicate of JsonSchemaPropertyAttribute for clarity and intent.

FunctionSchemaAttribute

OpenAI styled JSON Schema attribute for annotating classes for LLM function calls.

Note: It's a duplicate of StrictJsonSchemaAttribute for clarity and intent.

FunctionToolChoice

GeneratedImageData

OpenAI style Generated Image Data used by OpenAI and xAI. Represents the Url or the content of an image generated by Image Generation AI.

GeneratedText

Generated<T>

Represents the complete result envelope for content generated by AI services through the Unified API. Encapsulates generated values, metadata, usage statistics, and optional error information.

GenerationRecordOptions

Options that control how a GenerationRecord is created and stored after an AI generation request completes.

GenerationRecordOptions.GenerationMergeOptions

Defines how a new GenerationRecord should be merged into an existing one.

GenerationSettings

Serializable base class for AI generation settings.

GenerativeAudioRequest<TSelf, TInput, TOptions>

GenerativeAudioSettings

GenerativeImageRequest<TRequest, TProviderOptions>

GenerativeRequest<TSelf, TPrompt, TResult, TOptions>

Abstract base class for all generative AI tasks. Provides common properties and methods for handling prompts, models, outputs, and execution.

GenerativeServiceBase

GenerativeStreamExtensions

GenerativeStream<TDelta, TResult>

GenerativeTextRequest<TSelf, TInput, TResult, TEvent>

Base class for text generation tasks using LLM models. Supports instructions, role-based prompts, and attachments.

GenerativeVisualRequest<TSelf, TAsset, TEvent, TOptions>

GetCreditsRequest

Get total credits purchased and used for the authenticated user

GetFileRequest

GetModelRequest

GetSignedUrlRequest

GetVoiceRequest

GoogleDiffusionOptionsBase

Base class for Google diffusion model request options (Imagen, Veo). Contains parameters shared across Google's image and video generation APIs.

GoogleImagenOptions

Provider-specific request options for Google Imagen image generation. Pass this to ImageGenerationRequest via SetProviderOptions.

GoogleTypes

Types only used by Google API.
This shit is here instead of the Google assembly because this is used by GENTask and the UnityEditor Generator Windows.

GoogleTypes.UploadMetadata

GoogleVeoOptions

Provider-specific request options for Google Veo video generation. Pass this to VideoGenerationRequest via SetProviderOptions.

GrammarCustomToolFormat

A grammar defined by the user.

HostedToolChoice

Only for Responses API. Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools: https://platform.openai.com/docs/guides/tools

Allowed types (2025-09-21):

file_search
web_search_preview
computer_use_preview
code_interpreter
image_generation

HostedToolDefinitionBase

HyperParameters

The hyperparameters used for the fine-tuning job.

ImageAnalysis

Represents an image analysis output as an asset structure, designed to be used with Generated<ImageAnalysis>.

ImageBackgroundRemovalRequest

ImageContentData

ImageEditRequest

ImageEraseRequest

ImageGenerationOutput

An image generation request made by the model.

ImageGenerationRequest

ImageGenerationSettings

ImageGenerationTool

A tool that generates images using a model like gpt-image-1.

ImageGenerationToolSettings

ImageInpaintRequest

ImageOutpaintRequest

ImagePart

ImagePrice

Represents per-image pricing, optionally scoped by resolution and quality tier.

ImagePrompt

A specialized prompt for various image-related requests, such as image inpainting, rotation, animation, etc.
This class is used to pass the instruction and the image to the respective image model for processing.

ImageQualitySwitchAttribute

ImageSearchAndRecolorRequest

ImageSearchAndReplaceRequest

ImageSizeSwitchAttribute

ImageStyleTransferRequest

ImageUsage

InappropriateRequestException

IncompleteDetails

Details on why the response is incomplete. Will be null if the response is not incomplete.

IncompleteResponseException

InterruptedResponseException

InvalidPromptException

ItemReference

JsonSchemaFormat

KeyboardTypeAction

ListFilesRequest

ListModelsRequest

ListVoicesRequest

LocalShell

A tool that allows the model to execute shell commands in a local environment.

LocalShellCall

A call to run a command on the local shell.

LocalShellOutput

The output from a local shell tool call.

Location

LogProb

LogitBias

Optional. Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling.

The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. Defaults to null.

Logprobs

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. Defaults to 0.

MalformedRequestException

Exception thrown when a request is malformed or contains invalid parameters. This indicates that the request structure or content does not meet API requirements.

Mcp

Give the model access to additional tools via remote Model Context Protocol (MCP) servers.

McpApprovalRequest

A request for human approval of a tool invocation.
Model > User

McpApprovalResponse

A response to an MCP approval request.
User > Model

McpConnectorDefinition

McpException

McpHttpException

McpListToolsCallOutput

A list of tools available on an MCP server.
Model > User

McpOutput

An invocation of a tool on an MCP server. This is both a tool call (from model to user) and a tool call output (from user to model).
Model > User > And you should send the corresponding output back to the model

McpProtocalException

McpServerConnectorNotFoundException

McpServerDefinition

McpServerNotFoundException

McpToolApprovalFilter

Specify which of the MCP server's tools require approval.

McpToolChoice

McpToolDefinition

McpToolExecutionException

McpToolInfo

Information about a tool available on an MCP server.

McpToolPermissionInfo

McpToolRefList

List of allowed tool names or a filter object.

Message

MessageContent

Text:

ChatCompletion > ChatChoice[] > Message[] > MessageContent > StringOrPart > Text
MessageContentPart:
ChatCompletion > ChatChoice[] > Message[] > MessageContent > StringOrPart > MessageContentPart[]

MissingCatalogItemException

Exception thrown when a requested catalog item is not found in the specified catalog. Catalogs contain registered items such as models, tools, or other resources.

Model

ScriptableObject representation of a generative AI model with metadata, configuration, and pricing information. Supports token limits, ownership, creation time, and dynamic pricing for various content types (text, image, audio).

ModelBase

ModelCatalog

ScriptableObject database for storing model data. This database is used to keep track of the models available in the AI library.

ModelCatalog.Repo

Database for storing model data.

ModelErrorException

ModelExtensions

ModelFamily

Identifies a model family for a provider (for example, GPT, Gemini, or Llama). Keep this as string-based constants, not an enum, to avoid enum-order maintenance issues.

ModelInfo

ModelInterop

ModelNotFoundException

ModelNotReadyException

ModelPolicy

ModelPopupAttribute

ModelPrice

Abstract base class representing the pricing information for a model usage tier. Derived classes represent specific billing units such as per-token, per-image, or per-second.

ModelRefAttribute

ModelRequest<TSelf, TResult>

ModelStreamErrorException

ModelTimeoutException

ModelUtility

Moderation

Represents a moderation output as an asset structure, designed to be used with Generated<Moderation>.

ModerationPrompt

Not directly used as a prompt, but other prompts can convert to this type for moderation requests.
This class is used to pass the text and optional images to the moderation model for processing.

ModerationRequest

Audio not supported yet.

ModerationSettings

MouseActionBase

MoveAction

MusicGenerationRequest

Request for generating music from a text prompt.

NCount

The number of responses to generate. Must be between 1 and 10.

NetworkSettings

NoInputItemsException

Exception thrown when a request requires at least one input item but none were provided. This is a specialized case of MalformedRequestException for missing input data.

NotRegisteredModelException

Exception thrown when a requested AI model is not registered in the model catalog. This is a specialized case of MissingCatalogItemException for model-specific errors.

OcrDocument

Represents an OCR output as an asset structure, designed to be used with Generated<OcrDocument>.

OcrLineResult

OcrPrice

Represents per-page pricing, used for OCR and document analysis models.

OcrRequest

OcrUsage

OpenAIDalle3Options

Provider-specific request options for OpenAI DALL-E image generation. Pass this to ImageGenerationRequest via SetProviderOptions.

OpenAIDiffusionOptionsBase

Base class for OpenAI diffusion model request options (DALL-E, GPT-Image, Sora). Contains parameters shared across OpenAI's image and video generation APIs.

OpenAIGptImageOptions

Provider-specific request options for OpenAI GPT-Image (gpt-image-1) generation. Supports additional parameters such as background transparency and output compression. Pass this to ImageGenerationRequest via SetProviderOptions.

OpenAISoraOptions

Provider-specific request options for OpenAI Sora video generation. Pass this to VideoGenerationRequest via SetProviderOptions.

OpenAITypes

Types only used by OpenAI API.
This shit is here instead of the OpenAI assembly because this is used by GENTask and the UnityEditor Generator Windows.

OpenAITypes.ImageCompressionLevel

output_compression integer or null Optional Defaults to 100 The compression level (0-100%) for generated images. This parameter is only supported for gpt-image-1 with webp/jpeg output formats.

OpenAITypes.ImageReference

A reference to an image, either by file ID or base64-encoded data.

OpenPageAction

OutpaintSides

OutputExtensions

Extension methods for AIDevKit types.

PerplexityTypes

PresencePenalty

Defaults to 0 Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

PressKeyAction

ProjectContext

ProjectContextExtensions

Prompt

Represents a text prompt used in LLM (Large Language Model) AI interactions. Probably the most common type of prompt in AIDevKit.

PromptBase

PromptBase<T>

PromptExtensions

PromptFeedback

A set of the feedback metadata the prompt specified in GenerateContentRequest.Contents.

PromptTemplate

A reference to a predefined prompt template stored on the AI provider's servers.

This allows you to use complex prompt templates without having to include the full text of the prompt in your request. Instead, you can simply reference the prompt by its unique identifier and provide any necessary variables for substitution. This can help to keep your requests smaller and more manageable, especially when working with large or complex prompts.

Example Template: "Write a daily report for ${name} about today's sales. Include top 3 products."

ProviderBridgeAttribute

RateLimitExceededException

RealtimeApiException

Reasoning

ReasoningOptions

RedactedReasoning

Anthropic-specific class. Represents a block of content where the model's internal reasoning or "thinking" has been intentionally hidden (redacted) before being returned to the client.

ReferenceContentData

ReferencePart

RequestPrice

Represents a flat per-request pricing model.

RequestType

RequestUsage

ResponseFormat

ResponseMessage

ResponseRequest

SafetyFeedback

Safety feedback for an entire request.

This field is populated if content in the input and/or response is blocked due to safety settings. SafetyFeedback may not exist for every HarmCategory. Each SafetyFeedback will return the safety settings used by the request as well as the lowest HarmProbability that should be allowed in order to return a result.

SafetyIdentifier

A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers

SafetyRating

A safety rating associated with a {@link GenerateContentCandidate}

SafetySetting

Safety setting, affecting the safety-blocking behavior. Passing a safety setting for a category changes the allowed probability that content is blocked.

SafetySettingExtensions

ScreenshotAction

ScrollAction

SearchAction

Seed

Random seed for deterministic sampling (when supported):

Purpose — Reproduce the same output across runs with identical inputs.
Scope — Holds only if provider, model/deployment, version, and all params are unchanged.
null — Lets the service choose a random seed (non-deterministic).
Range — 0–9,223,372,036,854,775,807 (signed 64-bit long).
Support — Some models/services ignore seeds; if unsupported, this has no effect.

ServerDictionary

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.

ShellCommand

ShellCommandCatalog

ShellCommandCatalog.Repo

ShellCommandEntry

SignedUrl

SoundEffectGenerationRequest

Task for generating sound effects based on a text prompt.

SourceCode

Represents a code generation output as an asset structure, designed to be used with Generated<SourceCode>.

SpeechGenerationOptions

SpeechGenerationRequest

Task for generating synthetic speech (text-to-speech) using the specified model.

SpeechGenerationRequestBase<TSelf, TPrompt, TConfig>

SpeechGenerationSettings

SpeechSpeed

The speed of the model's spoken response as a multiple of the original speed. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.

This parameter is a post-processing adjustment to the audio after it is generated, it's also possible to prompt the model to speak faster or slower.

SpeechTranslationRequest

Task for translating speech into English text using the speech translation model.

SpokenLanguagePopupAttribute

StabilityEraseOptions

StabilityImageOptions

StabilityInpaintOptions

StabilityOutpaintOptions

StabilitySearchAndRecolorOptions

StabilitySearchAndReplaceOptions

StabilityStyleTransferOptions

StabilityTypes

StatusChangedEvent<T>

StatusExtensions

StreamOptions

StreamSettings

StreamingAudioConfig

StreamingGenerativeRequest<TSelf, TWire, TResult, TEvent, TOptions>

StrictJsonSchema

OpenAI styled JSON Schema for strict response formatting.

StrictJsonSchemaAttribute

OpenAI styled Strict JSON Schema attribute for annotating classes.

StrictJsonSchemaAttribute > StrictJsonSchema > JsonSchemaFormat(ResponseFormat)

StrictJsonSchemaExtensions

StructuredGeneratorBase<T>

StructuredOutputRequestBase<TSelf, TAsset>

StructuredOutputRequest<T>

Task for generating structured output (e.g., JSON) using an LLM model.

SubscriptionRequiredException

SystemMessage

Temperature

Sampling temperature: controls randomness in output.

Lower = deterministic
Higher = creative

Range: 0.0–2.0 (typical: 0.7–1.0).

TextChunk

Represents a chunk of text content in an LLM streaming response. Used for real-time display of AI-generated text as it arrives from the model.

TextContentData

TextCustomToolFormat

Unconstrained free-form text format.

TextGenerationSettings

Unified configuration settings for text generation across different APIs, including base LLM parameters and API-specific options.

TextPart

Text, Refusal, InputText, OutputText content part.

TextResponseOptions

TextSegment

Represents a detokenization output as an asset structure, designed to be used with Generated<TextSegment>.

ThinkingContentData

ThinkingPart

TimeWindowExtensions

TokenCount

Used to set 'max_tokens', 'max_completions_tokens', 'max_output_tokens', etc. Must be greater than or equal to 1024. Set it null to disable the limit.

TokenId

Represents a tokenization output as an asset structure, designed to be used with Generated<TokenId>.

TokenMetrics

Represents a token count output as an asset structure, designed to be used with Generated<TokenMetrics>

TokenPrice

Represents per-token pricing, distinguishing between input and output token types.

TokenPrompt

TokenUsage

TokenizationRequest

Tool

Base class for all tools, includes type.

ToolCall

ToolCallArguments

Represents tool call arguments as a specialized text chunk. When an LLM decides to invoke a tool/function, the arguments are streamed as JSON text through this chunk type.

ToolCallKey

ToolCallState

ToolChoice

This can be a String or an Object Specifies a tool the model should use. Use to force the model to call a specific tool.

ToolMessage

API don't send these anymore. It is only used to send the tool outputs from the 'client' side.

ToolOutput

ToolOutputTimeoutException

ToolReference

ToolResult<T>

ToolStatusEvent

Event raised when a tool's status changes.

ToolSupport

ToolTypeUtility

TopK

TopP

Transcript

TranscriptionPrice

Represents per-character pricing, used for transcription and character-based billing models.

TranscriptionRequest

Task for converting speech audio into text (speech-to-text).

TranscriptionRequestBase<TSelf>

TranscriptionSettings

TranscriptionUsage

TruncationStrategy

UnhandledToolCallException

UnifiedApiCallerExtensions

Beginner-friendly fluent extension methods that create request objects for generative AI. These helpers do not send any network calls until you invoke .ExecuteAsync().

Pattern: host.GENXxx().SetModel(...).ExecuteAsync()
Thin factories only; they return strongly-typed *Request objects.
No background work, no I/O, no async until .ExecuteAsync().

UnifiedApiCallerExtensionsAws

UnifiedApiCallerExtensionsEnterprise

Enterprise-only fluent extension methods for advanced image-edit tasks. These helpers only create request objects; network calls start at .ExecuteAsync().

UnifiedApiRequestBase<TSelf, TResult, TProviderOptions>

Base class for all Fluent API requests. Provides common properties and methods for configuring and executing requests.

UnknownAction

UnknownItem

UnsupportedEndpointException

Exception thrown when a requested endpoint is not supported by the specified API. Different APIs support different sets of endpoints, and this exception indicates an attempt to use an unsupported one.

UploadFileRequest

UploadedFile

Serializable implementation of IUploadedFile used by the SDK. Stores provider file metadata in a Unity-friendly form for runtime and editor workflows.

UploadedFileCatalog

ScriptableObject database for storing file data. This database is used to keep track of the files available in the AI library.

UploadedFileCatalog.Repo

Database for storing file data.

UrlCitation

UrlSearchSource

Usage

Usage metadata returned by AI service providers after a generation request. Contains token usage details for billing and monitoring.

UsageCalculator

Handles all cost calculation logic for Usage and UsageInfo.

UsageInfo

Usage<T>

UserMessage

ValueChangedEvent<T>

VerboseTranscript

Represents a verbose json transcription response returned by model, based on the provided input. Used by OpenAI, GroqCloud, and other compatible services.

VerboseTranscript.Segment

VerboseTranscript.WordObject

VideoContentData

VideoGenerationRequest

VideoGenerationSettings

VideoPart

Voice

VoiceCatalog

ScriptableObject database for storing voice data used for TTS (Text-to-Speech) and other voice-related tasks.

VoiceCatalog.Repo

Database for storing voice data.

VoiceChangeRequest

VoiceChangeSettings

VoiceInfo

Interface for voice data retrieved from various AI APIs. This interface defines the properties that all voice data should implement. It is used to standardize the voice data across different AI providers.

VoiceNotFoundException

VoicePolicy

VoicePopupAttribute

VoiceRequest<TSelf, TResult>

VoiceStyleConverter

VoiceUtility

WaitAction

WebSearch

Search the Internet for sources related to the prompt.

WebSearchAction

WebSearchFilter

Filters for the search.

WebSearchOutput

A tool call to perform a web search action.
This tool call does not have a corresponding output class, as the results are returned via text messages.

WebSearchPreview

This tool searches the web for relevant results to use in a response.

WebSearchPrice

Represents per-search pricing for models that include web search capability.

WebSearchSettings

WebSearchSource

WebSearchUsage

Structs

ApiAccess

ClipSpec

DocumentRef

FileRef

MediaSize

Represents a media size for images and videos with predefined presets for various AI models and social media platforms. Supports DALL-E, GPT Image, Sora, and common social media formats.

OpenAITypes.ImageQuality

The quality of the image that will be generated. HD creates images with finer details and greater consistency across the image. This param is only supported for OpenAIModel.DallE3.

ResponseStatusChangedEvent

ServiceTier

The service tier to use for the request. "auto" lets the system choose the appropriate tier based on context. Different providers may have different tier names and meanings. See provider documentation for details.

ToolCallEvent

Event raised when a tool call is requested by the model. Wraps the ToolCall domain model for event propagation.

ToolOutputEvent

Event raised when a tool produces output.

TranscriptDelta

TruncationType

UsageEvent

Event containing the usage metrics for the current operation and total conversation usage. Can be used to update the UI after each message is sent/received.

Weighted<T>

A wrapper to hold an item along with its associated weight value.

Interfaces

IAIResource

Represents data provided by an AI service provider like Model, Voice, or UploadedFile.

IAnnotationChunk

Base interface for annotation/citation data.

IAnnotationDeltaListener

Interface for listening to annotation delta events.

IAssistantsChatService

IAssistantsOptions

IAudioBufferStateListener

Interface for listening to audio buffer state change events.

IAudioRequestOptions

Provider-specific options for audio generation (TTS / voice) endpoints.

IChatApiStreamHandler

IChatCompletionsApiStreamHandler

IChatCompletionsOptions

IChatEventListener

IChatSettingsUpdater<TRequestSettings>

IComputerUseResult

IContentData

IConversationEventListener

Interface for listening to conversation events.

ICreditInfo

IEmbeddingRequestOptions

Provider-specific options for text/multimodal embedding endpoints.

IEmbeddingService

Service interface for text embedding generation.

IEmbeddingsOptions

IErrorEventListener

Interface for listening to error events.

IFileRequestOptions

Provider-specific options for file upload/management endpoints.

IFileSearchFilter

IFineTuningRequestOptions

Provider-specific options for fine-tuning endpoints.

IFineTuningResult

IGenerationOptions

IGenerativeRequest

Defines the common contract for all Unified API generative requests.

IGenerativeService<TInput, TOutput, TSettings>

Represents a generative AI service that produces a final output from an input.

IGenerativeStreamListener

IGenerativeStreamListener<TEvent, TAsset>

IGenerativeStream<TDelta, TResult>

IGenerativeTextRequest

IGenerativeVisualRequest

Common contract for image and video generation requests. "Visual" explicitly excludes audio ??this covers any generation request whose primary output is an image or video frame.

IHostedToolOptions

IImageAnalysisResult

IImageAnalysisTextResult

IImageDeltaListener

Interface for listening to image delta events.

IImageGeneration

Base marker interface for all image generation services.

IImageGenerationOptions

IImageGenerationService

Service interface for standard image generation (REST API).

IImageRequestOptions

Provider-specific options for image generation endpoints.

ILoadablePrompt

IManagementRequestOptions

Provider-specific options for resource management endpoints (e.g. listing, deleting models).

IMcp

IMcpApprovalRequestListener

Interface for listening to MCP approval request events.

IMcpApprovalSender

IModelInfo

Defines the contract for model metadata retrieved from AI provider APIs (e.g. GET /v1/models). All provider-specific model data classes implement this interface to ensure a consistent structure for model type, capabilities, token limits, pricing, and benchmark information.

IModeratable

IModerationOptions

IModerationRequestOptions

Provider-specific options for content moderation endpoints.

IOcrRequestOptions

Provider-specific options for OCR (optical character recognition) endpoints.

IPrompt

IProviderBridge

IProviderRequestOptions

Base marker interface for all provider (vendor)-specific request options.

Options exist because not every parameter is supported by every provider. Rather than polluting the shared FluentAPI with provider-specific fields, extra parameters are encapsulated in a dedicated options object and passed alongside the request.

All provider-specific option classes should implement this interface, either directly or through one of the endpoint-scoped sub-interfaces below.

IRealtimeApiStreamHandler

IRealtimeChatService

IRealtimeEventListener

IRealtimeOptions

IResponseEventListener

IResponseMessageProvider

IResponsesApiStreamHandler

IResponsesOptions

ISpeechToText

Base marker interface for all speech-to-text services.

ISpeechToTextOptions

ISpeechToTextService

Service interface for standard speech-to-text (REST API).

IStreamingAudioListener

IStreamingChatService

IStreamingChatService<TDelta, TResult, TSettings>

Interface for chat-based generative AI services that handle conversational interactions.

IStreamingGenerativeRequest<TEvent, TAsset>

IStreamingGenerativeService<TInput, TDelta, TOutput, TSettings>

Represents a generative AI service that can stream incremental output.

IStreamingImageGenerationService

Service interface for streaming image generation.

IStreamingImageListener

IStreamingSpeechToTextService

Service interface for streaming speech-to-text.

IStreamingTextToSpeechService

Service interface for streaming text-to-speech.

IStreamingTranscriptListener

ITextChunk

Base interface for streaming text data chunks.

ITextDeltaListener

Interface for listening to text delta events.

ITextGenerationOptions

ITextRequestOptions

Provider-specific options for text generation (chat / completion) endpoints.

ITextToSpeech

Base marker interface for all text-to-speech services.

ITextToSpeechOptions

ITextToSpeechService

Service interface for standard text-to-speech (REST API).

IToolCallOutput

IToolOutputListener

Interface for listening to tool output events.

IToolSettings

IToolStatusListener

Interface for listening to tool status events.

ITranscriptionRequestOptions

Provider-specific options for speech-to-text (transcription) endpoints.

IUploadedFile

Represents a normalized uploaded-file resource returned by provider APIs. This interface exposes shared file metadata so higher-level SDK code can remain provider-agnostic.

IUsageEventListener

Interface for listening to usage events.

IUsageProvider

IUserProfile

Attach this interface to your user class to enable AIDevKit features. This interface is used to provide user-specific context and settings.

IVideoGenerationOptions

IVideoRequestOptions

Provider-specific options for video generation endpoints.

Video generation parameters often overlap heavily with image generation options.

IVoiceInfo

IWebSocketAudioInputService

[DEPRECATED] This interface has been replaced by IWebSocketSpeechToTextService. Use IWebSocketSpeechToTextService.PushInputAudioBuffer() instead. This file will be removed in a future version.

IWebSocketGenerativeService<TInputBuffer, TDelta, TOutput, TSettings>

Represents a generative AI service that maintains a persistent WebSocket connection for bidirectional real-time communication.

IWebSocketImageGenerationService

Service interface for WebSocket-based image generation.

IWebSocketSpeechToTextService

Service interface for WebSocket-based speech-to-text.

IWebSocketTextToSpeechService

Service interface for WebSocket-based text-to-speech.

Enums

AmazonTypes.TitanImageQuality

AnnotationType

Api

Identifies the available AI service providers for API integrations.

This enum represents logical AI backends rather than pure network providers. Some entries may be cloud-based, self-hosted, local, or experimental.

AudioBufferState

Represents the state of an audio buffer.

CatalogType

ChatRole

CodeInterpreterStatus

CodeReferenceSource

ComparisonType

CompoundType

ConnectionMode

ContentFormat

ContentType

Identifies the content part type used across AI APIs (ChatCompletions, Responses, Assistants, and third-party providers).

ContextPurpose

CustomToolFormatType

ElevenLabsTypes.InputFormat

The format of input audio. Options are "pcm_s16le_16" or "other". For pcm_s16le_16, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform.

ElevenLabsTypes.MusicVocalType

The granularity of the timestamps in the transcription. "word" provides word-level timestamps and "character" provides character-level timestamps per word.

ElevenLabsTypes.OutputFormat

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. Default is mp3_44100_128.

ElevenLabsTypes.TimestampsGranularity

EmbedInputType

Type of input for embedding generation. RESTEnum has Marengo style string values.

EmbedTaskType

Google, Cohere Only. Task type for embedding content. It's in Google format, but it's converted to Cohere format with JsonConverter when using with Cohere provider.

EmbedTypes

FileResponseFormat

FileSourceType

FinishReason

The reason the model stopped generating tokens. It is also called "finish_reason" in some APIs.

GameGenre

GameTheme

GameType

GenerationStatus

GoogleTypes.AspectRatio

GoogleTypes.PersonGeneration

GoogleTypes.Resolution

HarmBlockThreshold

Block at and beyond a specified harm probability.

HarmCategory

Represents the category of harm that a piece of content may fall into. This is used in moderation tasks to classify content based on its potential harm.

HarmProbability

Probability that a prompt or candidate matches a harm category.

ImageAnalysisType

ImageEditType

IncludeOption

LanguageTone

McpOAuthType

MediaGenerationOp

Modality

Modality defines the data form a model accepts as input and returns as output. Even for similar generation tasks, models can differ in whether they use text, image, or audio data. The SDK uses this value to validate compatibility in model selection, request mapping, and UI filtering.

ModelCapability

Unified Model Capabilities Enum Combines capabilities across different model types for easier management.

ModelErrorType

ModelType

Types of AI Models. Multi-modal models such as Gemini should be classified under their primary function, typically as Language Models.

OSMask

OpenAITypes.AudioStreamFormat

OpenAITypes.Fidelity

OpenAITypes.ImageBackground

OpenAITypes.ImageDetail

OpenAITypes.ImageModeration

OpenAITypes.ImageStyle

The style of the generated images. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for OpenAIModel.DallE3.

Delegates

RecordMerger

A delegate that merges two GenerationRecord instances into one. Used to combine a base record with a newly generated record, e.g. for appending streaming chunks.