Create a response (OpenAI Responses API)

Request body · application/json

Type

object

Required fields

modelinput

Request body required

• modelstringRequired

• inputunionRequired

  Input content, as a string or message array

  oneOf branch 1

  Type: string
  oneOf branch 2

  Type: array

  • []objectOptional

• instructionsstringOptional

• max_output_tokensintegerOptional

• temperaturenumberOptional

  Sampling temperature. Specific support and limits depend on the selected model; no uniform defaults are guaranteed.

• top_pnumberOptional

  Nucleus sampling parameter. Specific support and limits depend on the selected model; no uniform defaults are guaranteed.

• streambooleanOptional

• toolsarrayOptional
  tools child fields (1)

  • []objectOptional

• tool_choiceunionOptional
  oneOf branch 1

  Type: string
  oneOf branch 2

  Type: object
• reasoningobjectOptional
  reasoning child fields (2)

  • effortstringOptional

    Enum

    ["low","medium","high"]

  • summarystringOptional

• previous_response_idstringOptional

• truncationstringOptional

  Enum

  ["auto","disabled"]

• parallel_tool_callsbooleanOptional

  Whether parallel tool calls are allowed depends on the selected model. Chat accepts a boolean; Responses accepts compatible protocol JSON values.

• storebooleanOptional

  Whether requests and responses may be stored depends on the selected model and supported service capabilities. This does not provide a general conversation storage API.

• prompt_cache_keystringOptional

  prompt cache correlation identifier; model dependent, with no guarantee of a cache hit or support. Chat accepts a string; Responses accepts compatible protocol JSON values.

• prompt_cache_retentionunknownOptional

  prompt cache retention control as a JSON value; model dependent. The platform provides no uniform enum, default, or cache retention guarantee.

• service_tierstringOptional

  Requested service tier, which may affect charges. Ignored by default and effective only when supported. Accepted values depend on the selected model.

• textobjectOptional

  Text output configuration, including format for structured output; support and limits depend on the selected model.

  text child fields (1)

  • formatobjectOptional

    Text and structured output format configuration, depending on the model.

    format child fields (4)

    • typestringOptional

      Output format identifiers supported by the selected model.

    • namestringOptional

      Structured output name.

    • schemaobjectOptional

      JSON Schema for structured output; must satisfy the selected model requirements.

      Additional properties

      true

    • strictbooleanOptional

      Whether to require strict structured output, depending on the model.

• context_managementunknownOptional

  Context management configuration; model dependent, with no promise of automatic summarization or persistent memory.

• stream_optionsobjectOptional

  Responses streaming parameters; use with stream=true. Only supported fields take effect.

  stream_options child fields (2)

  • include_usagebooleanOptional

    Request streaming usage; availability depends on the model.

  • include_obfuscationbooleanOptional

    Responses stream obfuscation control; ignored by default, effective only when supported.

HTTP 200

{
  "type": "string",
  "description": "SSE 事件流，协议事件/用量/结束符取当前接口，错误可能在流内。"
}

HTTP 401

HTTP 403

HTTP 429

HTTP 500