Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation
Theme

Suggested
Overview Models Agents Tools Audio & voice Production API reference

Shared

Models
AllModels = string or "gpt-6-astra" or "gpt-6.1-sol" or "gpt-6.1-terra" or 87 more or "o1-pro" or "o1-pro-2025-03-19" or "o3-pro" or 19 more
ComparisonFilter object { key, type, value }

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

CompoundFilter object { filters, type }

Combine multiple filters using and or or.

CustomToolInputFormat = Text { type } or Grammar { definition, syntax, type }

The input format for the custom tool. Default is unconstrained text.

DecisionInputJSON object { data, type }

A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON.

DecisionQuestionInputImage object { image_url, type, detail }

An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported.

DecisionQuestionInputPart = DecisionQuestionInputText { text, type } or DecisionQuestionInputImage { image_url, type, detail } or DecisionInputJSON { data, type }

A text, image, or JSON content part in a question instruction.

DecisionQuestionInputText object { text, type }
text: string
minLength0
maxLength10485760
type: "input_text" (default: "input_text")
ErrorObject object { code, message, param, 2 more }
FunctionDefinition object { name, description, parameters, strict }
FunctionParameters = map[unknown]

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

Metadata = map[string]

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.

Reasoning object { context, effort, generate_summary, 2 more }

Configuration options for reasoning models.

ReasoningEffort = "none" or "minimal" or "low" or 4 more

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

ResponseFormatJSONObject object { type }

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type: "json_object"

The type of response format being defined. Always json_object.

ResponseFormatJSONSchema object { json_schema, type }

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

ResponseFormatText object { type }

Default response format. Used to generate text responses.

type: "text"

The type of response format being defined. Always text.

ResponseFormatTextGrammar object { grammar, type }

A custom grammar for the model to follow when generating text. Learn more in the custom grammars guide.

grammar: string

The custom grammar for the model to follow.

type: "grammar"

The type of response format being defined. Always grammar.

ResponseFormatTextPython object { type }

Configure the model to generate valid Python code. See the custom grammars guide for more details.

type: "python"

The type of response format being defined. Always python.

ResponsesModel = string or "gpt-6-astra" or "gpt-6.1-sol" or "gpt-6.1-terra" or 87 more or "o1-pro" or "o1-pro-2025-03-19" or "o3-pro" or 19 more