Skip to main content
POST
응답 API를 사용하여 gpt-6-astra와 함께 텍스트, 이미지, 파일 및 대화 기록을 전송합니다. 예제에서는 웹 검색, 맞춤 함수 호출, 구조화된 출력, 추론 및 스트리밍도 보여 줍니다.
다음 OpenAI 응답 레퍼런스 에서는 전체 API 형식을 설명하며, 여기의 예제에서는 CometAPI에 맞게 해당 형식을 구성합니다.

대화 이어가기

텍스트 전용 대화에서는 사용자 메시지와 어시스턴트의 텍스트 응답을 유지한 다음, 다음 사용자 메시지를 추가합니다:
response.output_text 는 응답의 어시스턴트 텍스트를 결합하는 SDK 편의 속성입니다. 함수 호출 대화에는 아래에 설명된 대로 도구 호출 및 결과 항목도 필요합니다.

웹 검색 사용

정보를 검색하고 출처 인용을 포함하려면 web_search 도구를 추가합니다:
애플리케이션에 검색 결과 또는 인용이 필요한 경우 반환된 web_search_call 항목과 메시지의 URL 주석을 확인하세요. 다른 기본 제공 도구에는 각각의 구성이 필요하며, 자세한 내용은 다음 OpenAI 도구 가이드에서 확인할 수 있습니다..

사용자 지정 함수 호출

함수 인수를 정의하고 모델이 함수를 요청하도록 합니다:
함수 호출은 function_call 출력 항목으로 나타납니다. 해당 arguments 필드는 JSON으로 인코딩된 문자열입니다. 함수를 실행한 다음, 원래 입력과 반환된 출력 항목에서 응답 항목의 id 필드를 제외하여 다음 요청을 구성합니다. 함수의 name, arguments, call_id 값은 유지하고, 일치하는 function_call_outputcall_idoutput에 결과를 포함한 항목을 추가합니다.

구조화된 출력 요청

스키마를 따르는 JSON을 요청하려면 text.format을 사용합니다:
JSON을 파싱하기 전에 응답이 완료되었고 요청을 거부하지 않았는지 확인합니다. 출력 토큰(Token) 한도에 도달한 응답은 불완전할 수 있습니다.

추론 구성

모델의 추론 수준을 선택하려면 reasoning.effort 값을 설정합니다:
예시에서는 일반 작업에 low를 사용하고 추론 예시에는 high를 사용합니다. max_output_tokens에는 추론 토큰(Token)과 표시되는 출력 토큰(Token)이 모두 포함됩니다.

응답 스트리밍(Streaming)

서버 전송 이벤트를 수신하려면 stream 값을 true로 설정합니다:
텍스트 응답에는 response.created, response.in_progress, response.completed 같은 수명 주기 이벤트가 포함됩니다. 텍스트는 response.output_text.delta 이벤트로 도착합니다. 도구 및 추론 이벤트는 요청에 따라 달라지므로, 모든 응답에 같은 순서가 있다고 가정하지 말고 type에 따라 이벤트를 처리하세요.
다음에 대한 OpenAI 가이드를 참조하세요: 이미지 입력, 파일 입력, 구조화된 출력, 함수 호출(Function Calling), 대화 상태, 및 추론.

인증

Authorization
string
header
필수

Bearer token authentication. Use your CometAPI key.

본문

application/json
model
string
기본값:gpt-6-astra
필수

Model ID to use for this request. See the Models page for current options.

예시:

"gpt-6-astra"

input
필수

Text, image, or file inputs to the model, used to generate a response. Can be a simple string for text-only input, or an array of input items for multimodal content (images, files) and multi-turn conversations.

instructions
string

A system (or developer) message inserted into the model's context. When used with previous_response_id, instructions from the previous response are not carried over — this makes it easy to swap system messages between turns.

background
boolean

Whether to run the model response in the background. Background responses do not return output directly — you retrieve the result later via the response ID.

context_management
object[]

Context management configuration for this request. Controls how the model manages context when the conversation exceeds the context window.

conversation

The conversation this response belongs to. Items from the conversation are prepended to input for context. Input and output items are automatically added to the conversation after the response completes. Cannot be used with previous_response_id.

include
enum<string>[]

Additional output data to include in the response. Use this to request extra information that is not included by default.

사용 가능한 옵션:
web_search_call.action.sources,
code_interpreter_call.outputs,
computer_call_output.output.image_url,
file_search_call.results,
message.input_image.image_url,
message.output_text.logprobs,
reasoning.encrypted_content
max_output_tokens
integer

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

max_tool_calls
integer

The maximum number of total calls to built-in tools that can be processed in a response. This limit applies across all built-in tool calls, not per individual tool. Any further tool call attempts by the model will be ignored.

metadata
object

Set of up to 16 key-value pairs that can be attached to the response. Useful for storing additional information in a structured format. Keys have a maximum length of 64 characters; values have a maximum length of 512 characters.

parallel_tool_calls
boolean

Whether to allow the model to run tool calls in parallel.

previous_response_id
string

An ID for a stored response that is accessible to the selected model and request context. Cannot be combined with conversation. The conversation-history example sends prior input and output items explicitly.

prompt
object

Reference to a prompt template and its variables.

prompt_cache_key
string

A key used to cache responses for similar requests, helping optimize cache hit rates. Replaces the deprecated user field for caching purposes.

prompt_cache_retention
enum<string>
지원 중단

Legacy prompt-cache retention setting. Refer to the selected model documentation for prompt_cache_options and supported retention settings.

사용 가능한 옵션:
in_memory,
24h
reasoning
object

Reasoning configuration for the selected model.

safety_identifier
string

A stable identifier for your end-users, used to help detect policy violations. Should be a hashed username or email — do not send identifying information directly.

Maximum string length: 64
service_tier
enum<string>

Specifies the processing tier for the request. When set, the response will include the actual service_tier used.

  • auto: Uses the tier configured in project settings (default behavior).
  • default: Standard pricing and performance.
  • flex: Flexible processing with potential cost savings.
  • priority: Priority processing with faster response times.
사용 가능한 옵션:
auto,
default,
flex,
priority
store
boolean

Request response storage for later retrieval, when supported by the selected model and request context.

stream
boolean

If set to true, the response data will be streamed to the client as it is generated using server-sent events (SSE). Events include response.created, response.output_text.delta, response.completed, and more.

stream_options
object

Options for streaming responses. Only set this when stream is true.

temperature
number

Sampling temperature. Omit this field for GPT-6 Astra.

필수 범위: 0 <= x <= 2
text
object

Configuration for text output. Use this to request structured JSON output via JSON mode or JSON Schema.

tool_choice

Controls how the model selects which tool(s) to call.

  • auto (default): The model decides whether and which tools to call.
  • none: The model will not call any tools.
  • required: The model must call at least one tool.
  • An object specifying a particular tool to use.
tools
object[]

Tools available to the model. This page demonstrates web_search and custom function tools. Other tool types require their own configuration; see the official tool reference.

top_logprobs
integer

Number of token alternatives to include for models supporting log probabilities. Requires message.output_text.logprobs in include. Omit for GPT-6 Astra.

필수 범위: 0 <= x <= 20
top_p
number

Nucleus sampling threshold. Omit this field for GPT-6 Astra. For sampling overrides, adjust either top_p or temperature.

필수 범위: 0 <= x <= 1
truncation
enum<string>

The truncation strategy for handling inputs that exceed the model's context window.

  • auto: The model truncates the input by dropping items from the beginning of the conversation to fit.
  • disabled (default): The request fails with a 400 error if the input exceeds the context window.
사용 가능한 옵션:
auto,
disabled
user
string
지원 중단

Deprecated. Use safety_identifier and prompt_cache_key instead. A stable identifier for your end-user.

응답

200 - application/json

The generated Response object.

id
string

Unique identifier for the response.

예시:

"resp_example"

object
enum<string>

The object type, always response.

사용 가능한 옵션:
response
예시:

"response"

created_at
integer

Unix timestamp (in seconds) of when the response was created.

예시:

1788763707

status
enum<string>

The status of the response.

사용 가능한 옵션:
completed,
in_progress,
failed,
cancelled,
queued,
incomplete
예시:

"completed"

background
boolean

Whether the response was run in the background.

예시:

false

completed_at
integer | null

Unix timestamp of when the response was completed, or null if still in progress.

예시:

1788763711

error
object | null

Error information if the response failed, or null on success.

incomplete_details
object | null

Details about why the response is incomplete, if applicable.

instructions
string | null

The system instructions used for this response.

max_output_tokens
integer | null

The maximum output token limit that was applied.

model
string

The model used for the response.

예시:

"gpt-6-astra"

output
object[]

An array of output items generated by the model. Each item can be a message, function call, or other output type.

parallel_tool_calls
boolean

Whether parallel tool calls were enabled.

previous_response_id
string | null

The ID of the previous response, if this is a multi-turn conversation.

reasoning
object

The reasoning configuration that was used.

service_tier
string

The service tier actually used to process the request.

store
boolean

Whether the response was stored.

temperature
number

The temperature value used.

text
object

The text configuration used.

tool_choice

The tool choice setting used.

tools
object[]

The tools that were available for this response.

top_p
number

The top_p value used.

truncation
string

The truncation strategy used.

usage
object

Token usage statistics for this response.

user
string | null

The user identifier, if provided.

metadata
object

The metadata attached to this response.

content_filters
array | null

Content filter results applied to the response, if any.

frequency_penalty
number

The frequency penalty applied to the request.

max_tool_calls
integer | null

Maximum number of tool calls allowed, if set.

presence_penalty
number

The presence penalty applied to the request.

prompt_cache_key
string | null

Cache key for prompt caching, if applicable.

prompt_cache_retention
string | null

Prompt cache retention policy, if applicable.

safety_identifier
string | null

Safety system identifier for the response, if applicable.

top_logprobs
integer

Number of top log probabilities returned per token position.

마지막 수정일 2026년 9월 8일