The identity and technical contract details declared by the specification.
ChatCompletionRequestMessageContentPartRefusal
object
Schema for ChatCompletionRequestMessageContentPartRefusal. Fields: - type (required): Literal["refusal"] - refusal (required): str
2 properties
2 required
Credential
object
Credential for MCP server authentication. Passed at endpoint level (e.g., chat.completions.create) and matched to MCP servers by connection name. Wire format m…
2 properties
2 required
ChatCompletionResponseMessage
object
A chat completion message generated by the model. Fields: - content (required): str | None - refusal (required): str | None - toolcalls (optional): ChatComplet…
7 properties
3 required
EmbeddingRequest
object
Schema for EmbeddingRequest. Fields: - input (required): str | Annotated[list[str], MinLen(1), MaxLen(2048), ArrayTitle("EmbeddingRequestInputArray")] | Annota…
5 properties
2 required
ChatCompletionStreamResponseDelta
object
A chat completion delta generated by streamed model responses. Fields: - content (optional): str | None - functioncall (optional): ChatCompletionStreamResponse…
5 properties
ChatCompletionStreamResponseChoicesItemLogprobs
object
Log probability information for the choice. Fields: - content (required): list[ChatCompletionTokenLogprob] - refusal (required): list[ChatCompletionTokenLogpro…
2 properties
2 required
PredictionContent
object
Static predicted output content, such as the content of a text file that is being regenerated. Fields: - type (required): Literal["content"] - content (require…
2 properties
2 required
PendingCallResponse
object
Client-side tool call the SDK must execute.
4 properties
3 required
EmbeddingResponse
object
Schema for EmbeddingResponse. Fields: - data (required): list[Embedding] - model (required): str - object (required): Literal["list"] - usage (required): Usage
4 properties
4 required
MCPServerSpec
object
Structured MCP server specification. Slug-based: {"slug": "dedalus-labs/brave-search", "name": "github-integration", "version": "v1.0.0"} URL-based: {"url": "h…
5 properties
1 required
ModelId
string
Model identifier string (e.g., 'openai/gpt-5', 'anthropic/claude-3-5-sonnet').
Embedding
object
Represents an embedding vector returned by embedding endpoint. Fields: - index (required): int - embedding (required): list[float] - object (required): Literal…
3 properties
3 required
ChatCompletion
object
Chat completion response for Dedalus API. OpenAI-compatible chat completion response with Dedalus extensions. Maintains full compatibility with OpenAI API whil…
16 properties
5 required
DeferredCallResponse
object
Server-side call blocked until pending client calls complete. Carries full spec for stateless resumption on subsequent turns.
6 properties
2 required
LogprobsItem
object
Fields: noqa: D415. - token (optional): str - logprob (optional): float - bytes (optional): list[float]
3 properties
ChatCompletionRequestMessageContentPartFile
object
Learn about [file inputs](/docs/guides/text) for text generation. Fields: - type (required): Literal["file"] - file (required): File
2 properties
2 required
ImageGenerateRequest
object
Request to generate images.
14 properties
1 required
ResponseFormatJsonObject
object
JSON object response format. An older method of generating JSON responses. Using jsonschema is recommended for models that support it. Note that the model will…
1 property
1 required
Choice
object
A chat completion choice. OpenAI-compatible choice object for non-streaming responses. Part of the ChatCompletion response.
4 properties
2 required
ChatCompletionRequestMessageContentPartImage
object
Learn about [image inputs](/docs/guides/vision). Fields: - type (required): Literal["imageurl"] - imageurl (required): ImageUrl
2 properties
2 required
ChatCompletionRequestToolMessage
object
Schema for ChatCompletionRequestToolMessage. Fields: - role (required): Literal["tool"] - content (required): str | Annotated[list[ChatCompletionRequestToolMes…
3 properties
3 required
FunctionParameters
object
The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema refe…
ToolChoiceAny
object
The model will use any available tools. Fields: - disableparalleltooluse (optional): bool - type (required): Literal["any"]
2 properties
1 required
SpeechRequest
object
Schema for SpeechRequest. Fields: - model (required): str | Literal["tts-1", "tts-1-hd", "gpt-4o-mini-tts", "gpt-4o-mini-tts-2025-12-15"] - input (required): A…
7 properties
3 required
ToolChoiceTool
object
The model will use the specified tool with toolchoice.name. Fields: - disableparalleltooluse (optional): bool - name (required): str - type (required): Literal…
3 properties
2 required
HTTPValidationError
object
1 property
CreateTranscriptionResponseJson
object
Represents a transcription response returned by model, based on the provided input. Fields: - text (required): str - logprobs (optional): list[LogprobsItem] -…
3 properties
1 required
ChatCompletionMessageToolCall
object
A call to a function tool created by the model. Fields: - id (required): str - type (required): Literal["function"] - function (required): ChatCompletionMessag…
4 properties
3 required
ChatCompletionMessageToolCallChunk
object
Schema for ChatCompletionMessageToolCallChunk. Fields: - index (required): int - id (optional): str - type (optional): Literal["function"] - function (optional…
4 properties
1 required
OCRPage
object
Single page OCR result.
2 properties
2 required
ChatCompletionRequestMessageContentPartText
object
Learn about [text inputs](/docs/guides/text-generation). Fields: - type (required): Literal["text"] - text (required): str
2 properties
2 required
CreateTranslationResponseVerboseJson
object
Fields: noqa: D415. - language (required): str - duration (required): float - text (required): str - segments (optional): list[TranscriptionSegment]
4 properties
3 required
ModelCapabilities
object
Normalized model capabilities across all providers.
10 properties
ChatCompletionRequestSystemMessage
object
Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, use developer messages for thi…
3 properties
2 required
ChatCompletionStreamResponseChoicesItem
object
Schema for ChatCompletionStreamResponseChoicesItem. Fields: - delta (required): ChatCompletionStreamResponseDelta - logprobs (optional): ChatCompletionStreamRe…
4 properties
3 required
ThinkingConfigDisabled
object
Schema for ThinkingConfigDisabled. Fields: - type (required): Literal["disabled"]
1 property
1 required
ResponseFormatJsonSchemaSchema
object
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/).
JSONSchema
object
Structured Outputs configuration options, including a JSON Schema. Fields: - description (optional): str - name (required): str - schema (optional): ResponseFo…
4 properties
1 required
Endpoint
string
API endpoints we expose.
InputTokenDetails
object
Details about the input tokens billed for this request. Fields: - texttokens (optional): int - audiotokens (optional): int
2 properties
ModelProviderInfo
object
Typed provider metadata surfaced to SDKs.
2 properties
2 required
ResponsePromptParam
object
Stored prompt template reference (BYOK).
3 properties
1 required
ThinkingConfigEnabled
object
Schema for ThinkingConfigEnabled. Fields: - budgettokens (required): int - type (required): Literal["enabled"]
2 properties
2 required
ModelSettings
object
51 properties
Model
object
Unified model metadata across all providers. Combines provider-specific schemas into a single, consistent format. Fields that aren't available from a provider…
10 properties
3 required
ChatCompletionStreamResponse
object
Represents a streamed chunk of a chat completion response returned by the model, based on the provided input. [Learn more](/docs/guides/streaming-responses). F…
8 properties
5 required
UpstreamAPI
string
Upstream provider API types.
CacheControlEphemeral
object
Schema for CacheControlEphemeral. Fields: - ttl (optional): Literal["5m", "1h"] - type (required): Literal["ephemeral"]
2 properties
1 required
ValidationError
object
5 properties
3 required
ToolChoiceNone
object
The model will not be allowed to use tools. Fields: - type (required): Literal["none"]
1 property
1 required
ResponseFormatJsonSchema
object
JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](/docs/guides/structured-outputs). Fields: - type…
2 properties
2 required
ChoiceLogprobs
object
Log probability information for the choice.
2 properties
MCPServers
array
List of MCP server inputs (slugs or structured specs).
CompletionUsage
object
Usage statistics for the completion request. Fields: - completiontokens (required): int - prompttokens (required): int - totaltokens (required): int - completi…
5 properties
3 required
ChatCompletionRequestUserMessage
object
Messages sent by an end user, containing prompts or additional context information. Fields: - content (required): str | Annotated[list[ChatCompletionRequestUse…
3 properties
2 required
OCRDocument
object
Document input for OCR.
2 properties
1 required
FunctionCall
object
Deprecated and replaced by toolcalls. The name and arguments of a function that should be called, as generated by the model. Fields: - arguments (required): st…
2 properties
2 required
TranscriptTextUsageDuration
object
Usage statistics for models billed by audio input duration. Fields: - type (required): Literal['duration'] - seconds (required): float
2 properties
2 required
CreateTranslationResponseJson
object
Fields: noqa: D415. - text (required): str
1 property
1 required
OCRResponse
object
OCR response schema.
3 properties
2 required
ImagesResponse
object
Response from image generation.
2 properties
2 required
SafetySetting
object
Per-category safety setting that pairs a content category with a blocking threshold. Fields: - category (required): SafetyCategory - threshold (required): Safe…
2 properties
2 required
Body_edit_image_v1_images_edits_post
object
8 properties
2 required
Reasoning
object
gpt-5 and o-series models only Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning).
3 properties
CreateTranscriptionResponseVerboseJson
object
Represents a verbose json transcription response returned by model, based on the provided input. Fields: - language (required): str - duration (required): floa…
6 properties
3 required
ChatCompletionFunctions
object
Schema for ChatCompletionFunctions. Fields: - description (optional): str - name (required): str - parameters (optional): FunctionParameters
3 properties
1 required
ChatCompletionRequestAudio
object
Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. [Learn more](/docs/guides/audio). Fields: - voice (required):…
2 properties
2 required
MCPToolResult
object
Result of a single MCP tool execution. Provides visibility into MCP tool calls including the full input arguments and structured output, enabling debugging and…
6 properties
4 required
ResponsesRequest
object
Responses request schema with Dedalus extensions.
31 properties
Usage
object
The usage information for the request. Fields: - prompttokens (required): int - totaltokens (required): int
2 properties
2 required
ToolChoiceAuto
object
The model will automatically decide whether to use tools. Fields: - disableparalleltooluse (optional): bool - type (required): Literal["auto"]
2 properties
1 required
ResponsesResponse
object
Responses API response with Dedalus extensions.
36 properties
5 required
MCPToolChoice
object
2 properties
2 required
TranscriptionSegment
object
Fields: noqa: D415. - id (required): int - seek (required): int - start (required): float - end (required): float - text (required): str - tokens (required): l…
10 properties
10 required
TranscriptionWord
object
Fields: noqa: D415. - word (required): str - start (required): float - end (required): float
3 properties
3 required
ChatCompletionRequestDeveloperMessage
object
Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, developer messages replace the…
3 properties
2 required
Provider
string
Supported LLM providers.
ResponseConversationParam
object
Conversation reference for continuing a Responses session.
1 property
1 required
MCPCredentials
array
List of credentials for MCP server authentication.
ModelProviderRoute
object
One endpoint - upstream routing entry exposed by /v1/models.
2 properties
2 required
ChatCompletionMessageCustomToolCall
object
A call to a custom tool created by the model. Fields: - id (required): str - type (required): Literal["custom"] - custom (required): ChatCompletionMessageCusto…
3 properties
3 required
Body_create_translation_v1_audio_translations_post
object
5 properties
2 required
OCRRequest
object
OCR request schema.
2 properties
1 required
VoiceIdsOrCustomVoiceInline
object
Custom voice reference. Fields: - id (required): str
1 property
1 required
DedalusModel
object
Structured model selection entry used in request payloads. Supports OpenAI-style semantics (string model id) while enabling optional per-model default settings…
2 properties
1 required
ChatCompletionTokenLogprob
object
Token log probability information.
4 properties
4 required
ModelStatus
string
Model availability status.
ListModelsResponse
object
Response for /v1/models endpoint.
2 properties
1 required
Audio
object
Data about a previous audio response from the model. [Learn more](/docs/guides/audio). Fields: - id (required): str
1 property
1 required
ThinkingConfigAdaptive
object
Schema for ThinkingConfigAdaptive. Fields: - type (required): Literal["adaptive"]
1 property
1 required
MCPServerError
object
Error details for a single MCP server failure.
3 properties
1 required
ChatCompletionRequestFunctionMessage
object
Schema for ChatCompletionRequestFunctionMessage. Fields: - role (required): Literal["function"] - content (required): str | None - name (required): str
3 properties
3 required
ChatCompletionRequest
object
ChatCompletion request schema. Supports OpenAI-compatible parameters, provider-specific extensions, server-side execution, and agent orchestration features.
61 properties
1 required
TranscriptTextUsageTokens
object
Usage statistics for models billed by token usage. Fields: - type (required): Literal['tokens'] - inputtokens (required): int - inputtokendetails (optional): I…
5 properties
4 required
Body_create_transcription_v1_audio_transcriptions_post
object
6 properties
2 required
ResponseFormatText
object
Default response format. Used to generate text responses. Fields: - type (required): Literal["text"]
1 property
1 required
Models
array
List of models for multi-model routing.
ChatCompletionRequestMessageContentPartAudio
object
Learn about [audio inputs](/docs/guides/audio). Fields: - type (required): Literal["inputaudio"] - inputaudio (required): InputAudio
2 properties
2 required
ModelDefaults
object
Provider-declared default parameters for model generation.
4 properties
CompletionTokensDetails
object
Breakdown of tokens used in a completion. Fields: - acceptedpredictiontokens (optional): int - audiotokens (optional): int - reasoningtokens (optional): int -…
4 properties
Body_create_variation_v1_images_variations_post
object
6 properties
1 required
PromptTokensDetails
object
Breakdown of tokens used in the prompt. Fields: - audiotokens (optional): int - cachedtokens (optional): int
2 properties
Image
object
Single image object.
3 properties
ChatCompletionRequestAssistantMessage
object
Messages sent by the model in response to user messages. Fields: - content (optional): str | Annotated[list[ChatCompletionRequestAssistantMessageContentPart],…
7 properties
1 required
Tool
object
Schema for Tool. Fields: - type (optional): ToolTypes - function (required): Function
2 properties
1 required
Function
object
Schema for Function. Fields: - name (required): str
1 property
1 required
DedalusModelChoice
Dedalus model choice - either a string ID or DedalusModel configuration object.
The full machine-readable OpenAPI contract behind this narrative.
Other APIs Dedalus Labs publishes across the network.