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

Suggested
Overview Models Agents Tools Voice & Audio Production API reference
API Dashboard
Try ChatGPT
API Reference

Shared

ModelsExpand Collapse
AllModels = (string & {}) | ChatModel | "o1-pro" | "o1-pro-2025-03-19" | "o3-pro" | 16 more
ChatModel = "gpt-5.6-sol" | "gpt-5.6-terra" | "gpt-5.6-luna" | 80 more
ComparisonFilter { key, type, value }

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

CompoundFilter { filters, type }

Combine multiple filters using and or or.

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

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

ErrorObject { code, message, param, type }
FunctionDefinition { name, description, parameters, strict }
FunctionParameters = Record<string, 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 = Record<string, string> | null

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.

OAuthErrorCode = "invalid_grant" | "invalid_subject_token" | (string & {})
Reasoning { context, effort, generate_summary, 2 more }

gpt-5 and o-series models only

Configuration options for reasoning models.

ReasoningEffort = "none" | "minimal" | "low" | 4 more | null

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 { 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.

ResponseFormatJSONSchema { json_schema, type }

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

ResponseFormatText { type }

Default response format. Used to generate text responses.

ResponseFormatTextGrammar { grammar, type }

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

ResponseFormatTextPython { type }

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

ResponsesModel = (string & {}) | ChatModel | "o1-pro" | "o1-pro-2025-03-19" | "o3-pro" | 16 more