Table of Contents

Class OpenAIService

Namespace
Mythosia.AI.Services.OpenAI
Assembly
Mythosia.AI.dll
public class OpenAIService : OpenAICompatibleService, IAIService, IAIRunService, IAIRequestFeatureService, IFunctionRegisterable, IAIProcessingInfoService, IImageGenerationService
Inheritance
OpenAIService
Implements
Inherited Members
Extension Methods

Constructors

OpenAIService(string, HttpClient) 

public OpenAIService(string apiKey, HttpClient httpClient)

Parameters

apiKey string
httpClient HttpClient

OpenAIService(string, string, HttpClient)

Creates a OpenAIService with a specific model.

public OpenAIService(string apiKey, string model, HttpClient httpClient)

Parameters

apiKey string
model string
httpClient HttpClient

Properties

DefaultImageModel

The image model used when a request does not specify one explicitly. This is independent from the chat model exposed by Model.

public string DefaultImageModel { get; }

Property Value

string

FunctionResultsRequireContinuation

Whether observed tool results still require a separate provider round.

protected override bool FunctionResultsRequireContinuation { get; }

Property Value

bool

Gpt5ReasoningEffort

GPT-5 reasoning effort level. GPT-5 defaults to Medium.

public Gpt5Reasoning Gpt5ReasoningEffort { get; set; }

Property Value

Gpt5Reasoning

Gpt5ReasoningSummary

GPT-5 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_1ReasoningEffort

GPT-5.1 reasoning effort level. GPT-5.1 defaults to None.

public Gpt5_1Reasoning Gpt5_1ReasoningEffort { get; set; }

Property Value

Gpt5_1Reasoning

Gpt5_1ReasoningSummary

GPT-5.1 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5_1ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_1Verbosity

GPT-5.1 verbosity level. GPT-5.1 defaults to Medium.

public Verbosity? Gpt5_1Verbosity { get; set; }

Property Value

Verbosity?

Gpt5_2ReasoningEffort

GPT-5.2 reasoning effort level. GPT-5.2 defaults to None. GPT-5.2 Pro defaults to Medium.

public Gpt5_2Reasoning Gpt5_2ReasoningEffort { get; set; }

Property Value

Gpt5_2Reasoning

Gpt5_2ReasoningSummary

GPT-5.2 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5_2ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_2Verbosity

GPT-5.2 verbosity level. GPT-5.2 defaults to Medium.

public Verbosity? Gpt5_2Verbosity { get; set; }

Property Value

Verbosity?

Gpt5_3ReasoningEffort

GPT-5.3 reasoning effort level. GPT-5.3 Codex defaults to Medium.

public Gpt5_3Reasoning Gpt5_3ReasoningEffort { get; set; }

Property Value

Gpt5_3Reasoning

Gpt5_3ReasoningSummary

GPT-5.3 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5_3ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_3Verbosity

GPT-5.3 verbosity level. GPT-5.3 defaults to Medium.

public Verbosity? Gpt5_3Verbosity { get; set; }

Property Value

Verbosity?

Gpt5_4ReasoningEffort

GPT-5.4 reasoning effort level. GPT-5.4 defaults to None. GPT-5.4 Pro defaults to Medium.

public Gpt5_4Reasoning Gpt5_4ReasoningEffort { get; set; }

Property Value

Gpt5_4Reasoning

Gpt5_4ReasoningSummary

GPT-5.4 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5_4ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_4Verbosity

GPT-5.4 verbosity level. GPT-5.4 defaults to Medium.

public Verbosity? Gpt5_4Verbosity { get; set; }

Property Value

Verbosity?

Gpt5_5ReasoningEffort

GPT-5.5 reasoning effort level. GPT-5.5 defaults to Medium. GPT-5.5 Pro defaults to High.

public Gpt5_5Reasoning Gpt5_5ReasoningEffort { get; set; }

Property Value

Gpt5_5Reasoning

Gpt5_5ReasoningSummary

GPT-5.5 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5_5ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_5Verbosity

GPT-5.5 verbosity level. GPT-5.5 defaults to Medium.

public Verbosity? Gpt5_5Verbosity { get; set; }

Property Value

Verbosity?

Gpt5_6ReasoningEffort

GPT-5.6 reasoning effort level. The model default is Medium.

public Gpt5_6Reasoning Gpt5_6ReasoningEffort { get; set; }

Property Value

Gpt5_6Reasoning

Gpt5_6ReasoningMode

GPT-5.6 reasoning execution mode. Pro mode is an API parameter, not a separate model ID.

public Gpt5_6ReasoningMode Gpt5_6ReasoningMode { get; set; }

Property Value

Gpt5_6ReasoningMode

Gpt5_6ReasoningSummary

GPT-5.6 reasoning summary mode. Defaults to Auto. Set to null to disable reasoning summaries.

public ReasoningSummary? Gpt5_6ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt5_6Verbosity

GPT-5.6 verbosity level. The model default is Medium.

public Verbosity? Gpt5_6Verbosity { get; set; }

Property Value

Verbosity?

Gpt6ReasoningEffort

GPT-6 reasoning effort level. Auto uses the library default of Medium. GPT-6 Sol and Luna also support None. GPT-6 Astra and GPT-6.1 Sol require at least Low.

public Gpt6Reasoning Gpt6ReasoningEffort { get; set; }

Property Value

Gpt6Reasoning

Gpt6ReasoningMode

GPT-6 reasoning execution mode. Pro is an API parameter, not a separate model ID.

public Gpt6ReasoningMode Gpt6ReasoningMode { get; set; }

Property Value

Gpt6ReasoningMode

Gpt6ReasoningSummary

GPT-6 reasoning summary mode. Defaults to Auto. Set to null to omit summaries. Summaries are also omitted when reasoning is None.

public ReasoningSummary? Gpt6ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Gpt6Verbosity

GPT-6 verbosity level. Null uses Medium.

public Verbosity? Gpt6Verbosity { get; set; }

Property Value

Verbosity?

HasPendingRunContinuation

Whether the transport will continue this run without a new user request.

protected override bool HasPendingRunContinuation { get; }

Property Value

bool

LastReasoningSummary

Contains the reasoning summary from the last non-streaming API call when the provider returns a reasoning output item. Remains null when summaries are disabled or the provider omits the optional summary output despite accepting reasoning.summary.

public string? LastReasoningSummary { get; }

Property Value

string

O3ReasoningSummary

o3 reasoning summary mode. This is opt-in because OpenAI requires a verified organization for reasoning summaries. Leave null to request ordinary o3 reasoning without a summary.

public ReasoningSummary? O3ReasoningSummary { get; set; }

Property Value

ReasoningSummary?

Provider

The AI provider for this service

public override string Provider { get; }

Property Value

string

SupportsAsyncFunctionCalls

Whether this provider and model accept native asynchronous function calls.

protected override bool SupportsAsyncFunctionCalls { get; }

Property Value

bool

Methods

ApplyCapabilityRequestProfile(AIRequestProfile)

Applies only execution-local profile settings needed to describe capabilities.

protected override void ApplyCapabilityRequestProfile(AIRequestProfile profile)

Parameters

profile AIRequestProfile

Remarks

Common builder overrides are already captured. Custom providers may override this hook with SetExecutionSetting calls for native mode flags. Do not prepare execution, reserve token budgets, invoke callbacks, validate requests, or modify service/caller-owned state. Execution profile hooks are intentionally not called during inspection.

ApplyProviderSpecificRequestProfile(AIRequestProfile) 

protected override Action ApplyProviderSpecificRequestProfile(AIRequestProfile profile)

Parameters

profile AIRequestProfile

Returns

Action

ApplyRequestProfile(AIRequestProfile) 

protected override Action ApplyRequestProfile(AIRequestProfile profile)

Parameters

profile AIRequestProfile

Returns

Action

CaptureRequestSettings(IDictionary<string, object?>)

Captures provider and common defaults. Overrides copy native mutable option values.

protected override void CaptureRequestSettings(IDictionary<string, object?> settings)

Parameters

settings IDictionary<string, object>

CollectPendingStreamingFunctionResultsAsync(CancellationToken)

Waits for pending results unless a duplex transport needs another model turn.

protected override Task<IReadOnlyList<FunctionCallResultBatch>> CollectPendingStreamingFunctionResultsAsync(CancellationToken cancellationToken)

Parameters

cancellationToken CancellationToken

Returns

Task<IReadOnlyList<FunctionCallResultBatch>>

ConnectRunWebSocketAsync(CancellationToken)

Connects one Responses WebSocket at the configured HTTP API base address. Override for a custom transport.

protected virtual Task<WebSocket> ConnectRunWebSocketAsync(CancellationToken cancellationToken)

Parameters

cancellationToken CancellationToken

Returns

Task<WebSocket>

CreateFunctionMessageRequest()

Creates HTTP request with function definitions

protected override HttpRequestMessage CreateFunctionMessageRequest()

Returns

HttpRequestMessage

CreateMessageRequest()

Creates the HTTP request message for the AI service

protected override HttpRequestMessage CreateMessageRequest()

Returns

HttpRequestMessage

CreateRunSessionAsync(Message, StreamOptions, AIRequestContext?, CancellationToken)

Creates a provider session for a run without changing legacy request transports.

protected override Task<AIService.RunSession> CreateRunSessionAsync(Message message, StreamOptions executionOptions, AIRequestContext? context, CancellationToken cancellationToken)

Parameters

message Message
executionOptions StreamOptions
context AIRequestContext
cancellationToken CancellationToken

Returns

Task<AIService.RunSession>

CreateStreamParseFailure(string, Exception, StreamDiagnostics)

Lets providers turn a malformed SSE data event into an explicit terminal error. Returning null preserves the tolerant behavior used by legacy compatible providers.

protected override StreamingContent? CreateStreamParseFailure(string jsonData, Exception exception, StreamDiagnostics diagnostics)

Parameters

jsonData string
exception Exception
diagnostics StreamDiagnostics

Returns

StreamingContent

EditImagesAsync(ImageEditRequest, CancellationToken)

Generates one or more images using existing images as references.

public Task<ImageGenerationResult> EditImagesAsync(ImageEditRequest request, CancellationToken cancellationToken = default)

Parameters

request ImageEditRequest
cancellationToken CancellationToken

Returns

Task<ImageGenerationResult>

EnrichStreamAssistantMessage(Message)

Allows a provider to attach state collected while streaming before the assistant message is added to the conversation history.

protected override void EnrichStreamAssistantMessage(Message assistantMessage)

Parameters

assistantMessage Message

ExtractFunctionCalls(string)

Extracts every function call from one API response.

protected override (string content, FunctionCallBatch functionCalls) ExtractFunctionCalls(string response)

Parameters

response string

Returns

(string content, FunctionCallBatch functionCalls)

ExtractResponseContent(string)

Extracts the response content from the API response

protected override string ExtractResponseContent(string responseContent)

Parameters

responseContent string

Returns

string

GenerateImagesAsync(ImageGenerationRequest, CancellationToken)

Generates one or more images from a text prompt.

public Task<ImageGenerationResult> GenerateImagesAsync(ImageGenerationRequest request, CancellationToken cancellationToken = default)

Parameters

request ImageGenerationRequest
cancellationToken CancellationToken

Returns

Task<ImageGenerationResult>

GetCompletionAsync(Message) 

public override Task<string> GetCompletionAsync(Message message)

Parameters

message Message

Returns

Task<string>

GetCompletionWithImageAsync(string, string, CancellationToken) 

public override Task<string> GetCompletionWithImageAsync(string prompt, string imagePath, CancellationToken cancellationToken = default)

Parameters

prompt string
imagePath string
cancellationToken CancellationToken

Returns

Task<string>

GetConversationCompactionBlockReason()

Returns a reason when protocol state requires retaining the original conversation prefix.

protected override string? GetConversationCompactionBlockReason()

Returns

string

GetImageCapabilities(string?)

Inspects an image generation model independently of the selected chat model, without HTTP.

public override ImageModelCapabilities GetImageCapabilities(string? model = null)

Parameters

model string

Returns

ImageModelCapabilities

Remarks

A null model uses the provider's image default. Unknown does not mean unsupported.

GetInputTokenCountAsync()

Gets the token count for the current conversation

public override Task<uint> GetInputTokenCountAsync()

Returns

Task<uint>

GetInputTokenCountAsync(string)

Gets the token count for a specific prompt

public override Task<uint> GetInputTokenCountAsync(string prompt)

Parameters

prompt string

Returns

Task<uint>

GetModelMaxOutputTokens()

Returns the maximum output tokens allowed for the current model. Override in each service to provide model-specific limits.

protected override uint GetModelMaxOutputTokens()

Returns

uint

GetSpeechAsync(string, string, string)

Generates speech audio from text using OpenAI's TTS model

public Task<byte[]> GetSpeechAsync(string inputText, string voice = "alloy", string model = "tts-1")

Parameters

inputText string
voice string
model string

Returns

Task<byte[]>

OnStreamRoundFailed()

Lets providers discard state collected during a failed streaming round.

protected override void OnStreamRoundFailed()

OnStreamRoundStarting()

Allows a provider to reset state scoped to a single streaming round.

protected override void OnStreamRoundStarting()

ParseStreamChunk(string, StreamOptions)

Parses a single SSE JSON chunk into a provider-neutral stream chunk. Each provider overrides this to handle its specific JSON format.

protected override OpenAICompatibleService.OpenAIStreamChunk ParseStreamChunk(string jsonData, StreamOptions options)

Parameters

jsonData string
options StreamOptions

Returns

OpenAICompatibleService.OpenAIStreamChunk

ReadStreamingResponseLinesAsync(HttpResponseMessage, StreamDiagnostics, CancellationToken)

Reads transport events in the line format consumed by the common parser.

protected override IAsyncEnumerable<string> ReadStreamingResponseLinesAsync(HttpResponseMessage response, StreamDiagnostics diagnostics, CancellationToken cancellationToken)

Parameters

response HttpResponseMessage
diagnostics StreamDiagnostics
cancellationToken CancellationToken

Returns

IAsyncEnumerable<string>

ResolveRequestCapabilities()

Resolves adapter support using RequestSetting and CurrentRequestFeatures without side effects.

protected override AIModelCapabilities ResolveRequestCapabilities()

Returns

AIModelCapabilities

Remarks

Custom providers may override this hook. The default preserves compatibility by returning Unknown. Overrides must not send requests, consume options, change history or invoke user callbacks.

ResolveRequestTimeoutSeconds(FunctionCallingPolicy)

OpenAI timeout policy. GPT-5, GPT-6, and slow pro reasoning workloads (legacy *-pro model IDs and reasoning.mode=pro) can take longer than the 100s default, so when the default is in effect they get longer timeouts. Explicit non-default timeouts are respected.

protected override int? ResolveRequestTimeoutSeconds(FunctionCallingPolicy policy)

Parameters

policy FunctionCallingPolicy

Returns

int?

ResolveSpeedSupport(InferenceSpeed)

Locally resolves processing-mode support without checking account entitlement or live capacity.

protected override CapabilitySupport ResolveSpeedSupport(InferenceSpeed speed)

Parameters

speed InferenceSpeed

Returns

CapabilitySupport

SendStreamingRequestAsync(HttpRequestMessage, CancellationToken)

Opens a provider streaming round using the request's transport.

protected override Task<HttpResponseMessage> SendStreamingRequestAsync(HttpRequestMessage request, CancellationToken cancellationToken)

Parameters

request HttpRequestMessage
cancellationToken CancellationToken

Returns

Task<HttpResponseMessage>

StreamParseJson(string)

Parses streaming JSON data

protected override string StreamParseJson(string jsonData)

Parameters

jsonData string

Returns

string

StreamRoundAsync(StreamOptions, bool, FunctionCallingPolicy, CancellationToken)

Executes a single streaming round: sends an HTTP request, reads the SSE stream, yields chunks, and handles function execution if detected. Yield a FunctionResult to signal the template to continue to the next round. Pending native asynchronous calls also keep the round loop active until their results have been delivered and the model finishes.

protected override IAsyncEnumerable<StreamingContent> StreamRoundAsync(StreamOptions options, bool useFunctions, FunctionCallingPolicy policy, CancellationToken cancellationToken)

Parameters

options StreamOptions
useFunctions bool
policy FunctionCallingPolicy
cancellationToken CancellationToken

Returns

IAsyncEnumerable<StreamingContent>

TranscribeAudioAsync(byte[], string, string?)

Transcribes a completed audio recording to text using OpenAI's GPT-Transcribe model.

public Task<string> TranscribeAudioAsync(byte[] audioData, string fileName, string? language = null)

Parameters

audioData byte[]
fileName string
language string

Returns

Task<string>

ValidateRequestFeatures(AIRequestFeatures)

Reject unsupported features before any network request or history mutation.

protected override void ValidateRequestFeatures(AIRequestFeatures features)

Parameters

features AIRequestFeatures

ValidateStreamTermination(bool, bool, StreamDiagnostics)

Lets providers require an explicit successful terminal event before committing a streamed assistant message or executing a collected function call.

protected override StreamingContent? ValidateStreamTermination(bool doneMarkerReceived, bool completionEventReceived, StreamDiagnostics diagnostics)

Parameters

doneMarkerReceived bool
completionEventReceived bool
diagnostics StreamDiagnostics

Returns

StreamingContent

WithGpt5Parameters(Gpt5Reasoning, ReasoningSummary?)

Sets GPT-5 specific parameters. Reasoning effort: Minimal, Low, Medium (default), High. Reasoning summary: Auto (default), Concise, Detailed, or null to disable.

public OpenAIService WithGpt5Parameters(Gpt5Reasoning reasoningEffort = Gpt5Reasoning.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto)

Parameters

reasoningEffort Gpt5Reasoning
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithGpt5_1Parameters(Gpt5_1Reasoning, Verbosity, ReasoningSummary?)

Sets GPT-5.1 specific parameters. Reasoning effort: None (default), Low, Medium, High. Verbosity: Low, Medium (default), High. Reasoning summary: Auto (default), Concise, Detailed, or null to disable.

public OpenAIService WithGpt5_1Parameters(Gpt5_1Reasoning reasoningEffort = Gpt5_1Reasoning.None, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto)

Parameters

reasoningEffort Gpt5_1Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithGpt5_2Parameters(Gpt5_2Reasoning, Verbosity, ReasoningSummary?)

Sets GPT-5.2 specific parameters. Reasoning effort: None (default), Low, Medium, High, XHigh. GPT-5.2 Pro supports Medium, High, XHigh. GPT-5.2 Codex supports Low, Medium (default), High, XHigh. Verbosity: Low, Medium (default), High. Reasoning summary: Auto (default), Concise, Detailed, or null to disable.

public OpenAIService WithGpt5_2Parameters(Gpt5_2Reasoning reasoningEffort = Gpt5_2Reasoning.None, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto)

Parameters

reasoningEffort Gpt5_2Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithGpt5_3Parameters(Gpt5_3Reasoning, Verbosity, ReasoningSummary?)

Sets GPT-5.3 specific parameters. Reasoning effort: None (default for Instant), Low, Medium (default for Codex), High, XHigh. GPT-5.3 Codex supports Low, Medium (default), High, XHigh. Verbosity: Low, Medium (default), High. Reasoning summary: Auto (default), Concise, Detailed, or null to disable.

public OpenAIService WithGpt5_3Parameters(Gpt5_3Reasoning reasoningEffort = Gpt5_3Reasoning.None, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto)

Parameters

reasoningEffort Gpt5_3Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithGpt5_4Parameters(Gpt5_4Reasoning, Verbosity, ReasoningSummary?)

Sets GPT-5.4 specific parameters. Reasoning effort: None (default), Low, Medium, High, XHigh. GPT-5.4 Pro supports Medium, High, XHigh. Verbosity: Low, Medium (default), High. Reasoning summary: Auto (default), Concise, Detailed, or null to disable.

public OpenAIService WithGpt5_4Parameters(Gpt5_4Reasoning reasoningEffort = Gpt5_4Reasoning.None, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto)

Parameters

reasoningEffort Gpt5_4Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithGpt5_5Parameters(Gpt5_5Reasoning, Verbosity, ReasoningSummary?)

Sets GPT-5.5 specific parameters. Reasoning effort: None, Low, Medium (default), High, XHigh. GPT-5.5 Pro defaults to High. Verbosity: Low, Medium (default), High. Reasoning summary: Auto (default), Concise, Detailed, or null to disable.

public OpenAIService WithGpt5_5Parameters(Gpt5_5Reasoning reasoningEffort = Gpt5_5Reasoning.Auto, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto)

Parameters

reasoningEffort Gpt5_5Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithGpt5_6Parameters(Gpt5_6Reasoning, Verbosity, ReasoningSummary?, Gpt5_6ReasoningMode)

Sets GPT-5.6 specific parameters. Reasoning effort: None, Low, Medium (default), High, XHigh, Max. Verbosity: Low, Medium (default), High. Pro is a reasoning mode and does not change the selected model ID.

public OpenAIService WithGpt5_6Parameters(Gpt5_6Reasoning reasoningEffort = Gpt5_6Reasoning.Medium, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto, Gpt5_6ReasoningMode reasoningMode = Gpt5_6ReasoningMode.Standard)

Parameters

reasoningEffort Gpt5_6Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?
reasoningMode Gpt5_6ReasoningMode

Returns

OpenAIService

WithGpt6Parameters(Gpt6Reasoning, Verbosity, ReasoningSummary?, Gpt6ReasoningMode)

Sets GPT-6 specific parameters. Reasoning effort: Low, Medium (library default), High, XHigh, Max; GPT-6 Sol and Luna also support None. GPT-6.1 Sol uses these settings and requires at least Low. Verbosity: Low, Medium (default), High. Pro is a reasoning mode and does not change the selected model ID.

public OpenAIService WithGpt6Parameters(Gpt6Reasoning reasoningEffort = Gpt6Reasoning.Medium, Verbosity verbosity = Verbosity.Medium, ReasoningSummary? reasoningSummary = ReasoningSummary.Auto, Gpt6ReasoningMode reasoningMode = Gpt6ReasoningMode.Standard)

Parameters

reasoningEffort Gpt6Reasoning
verbosity Verbosity
reasoningSummary ReasoningSummary?
reasoningMode Gpt6ReasoningMode

Returns

OpenAIService

WithO3Parameters(Gpt5Reasoning, ReasoningSummary?)

Sets o3 reasoning parameters. Reasoning summaries are disabled by default and require an OpenAI organization that is verified for summary generation.

public OpenAIService WithO3Parameters(Gpt5Reasoning reasoningEffort = Gpt5Reasoning.Medium, ReasoningSummary? reasoningSummary = null)

Parameters

reasoningEffort Gpt5Reasoning
reasoningSummary ReasoningSummary?

Returns

OpenAIService

WithOpenAIParameters(float?, float?, int?)

Fine-tunes the response with specific OpenAI parameters

public OpenAIService WithOpenAIParameters(float? presencePenalty = null, float? frequencyPenalty = null, int? bestOf = null)

Parameters

presencePenalty float?
frequencyPenalty float?
bestOf int?

Returns

OpenAIService
Edit this page