Skip to content

채팅 이미지 생성 (비스트리밍)

POST
/v1/chat/completions
  • OpenAI Chat Completions API와 호환되는 이미지 생성 채팅 엔드포인트(멀티모달 메시지)
  • messagestext로 창작 요구사항을 설명하고, 선택적으로 image_url을 참조 이미지로 첨부
  • 기본값 stream: false; 생성 또는 편집된 이미지 결과를 포함한 전체 완성을 한 번에 반환
  • 공식 문서: Images create

Authorizations

bearer
Type
HTTP (bearer)

Request Body

application/json
object

사용할 모델 ID. 이미지 생성에는 gpt-4o-image 등 이미지 모델을 자주 사용합니다.

object[]
Required

대화 메시지 목록. 이미지 생성 시 user 메시지 content는 멀티모달 배열(text + 선택적 image_url)입니다.
system 메시지도 일반 문자열 content를 사용할 수 있습니다(OpenAI와 동일).

Sampling temperature between 0 and 2. Higher values (e.g. 0.8) make output more random; lower values (e.g. 0.2) make it more focused. We generally recommend changing this or top_p, but not both.

Nucleus sampling alternative to temperature. The model considers tokens with top_p probability mass (e.g. 0.1 = top 10%). We generally recommend changing this or temperature, but not both.

Default 1. How many chat completion choices to generate per input message.

기본값 false. 비스트리밍 이미지 생성에서는 생략하거나 false로 설정해 전체 JSON 응답을 한 번에 받습니다.

Default null. Up to 4 sequences where the API stops generating further tokens.

Default inf. Maximum tokens to generate in the completion.

Total length of input + output tokens is limited by the model context length.

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the chance of new topics.

Default 0. Number between -2.0 and 2.0. Positive values penalize new tokens based on their frequency in the text so far, reducing repetition.

Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object mapping token IDs to bias values from -100 to 100.

Unique identifier for your end user. Helps OpenAI monitor and detect abuse. Learn more.

Object specifying the output format. Set { "type": "json_object" } to enable JSON mode.

Beta feature. If set, the system will try to sample deterministically; use system_fingerprint in the response to monitor backend changes.

List of tools the model may call. Currently only functions as tools are supported.

Controls which function the model calls, if any. none / auto / specify function name.

Responses

application/json
object
object[]
Required
object
Required

Playground

Authorization
Body

Samples