메인 콘텐츠로 건너뛰기
POST
/
v1
/
chat
/
completions
curl --request POST \
  --url https://api.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}
'
{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gemini-3-pro-preview",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm pleased to introduce myself.\n\nI'm a Large Language Model, trained and developed by Google.\n\nSimply put, you can think of me as a \"smart brain\" that has been trained on massive amounts of text data and is able to understand and generate human language. My core capability is processing and generating text. Specifically, I can do the following:\n\n**1. Information Query & Knowledge Answering**\nI can act like a \"talking encyclopedia,\" answering various questions, whether they're about scientific knowledge, historical events, or everyday facts.\n\n**2. Creative Writing & Text Generation**\nI can create various types of text based on your requirements, such as:\n*   **Writing**: Poetry, stories, scripts, emails, speeches, advertising copy, etc.\n*   **Planning**: Travel plans, study outlines, event proposals, etc.\n*   **Brainstorming**: Working with you to generate new ideas and spark creativity.\n\n**3. Translation & Language Processing**\nI'm proficient in multiple languages and can provide fast, fluent translation services. I can also help you polish, proofread, summarize, or rewrite text to make your expression clearer and more professional.\n\n**4. Programming & Code Assistance**\nI can write code snippets, explain code logic, debug errors, or \"translate\" code from one programming language to another, making me a helpful companion for programmers.\n\n**5. Logical Analysis & Reasoning**\nI can help you analyze complex problems, organize logical chains, and make inferences and summaries based on the information you provide.\n\n---\n\n**In summary**, my goal is to be a powerful and useful tool that helps you obtain information more efficiently, complete tasks, and spark creativity through natural language communication.\n\n**Remember:** I'm an artificial intelligence, my knowledge comes from the data I've learned, and it may not be the most up-to-date. Sometimes I may also make mistakes, so for very important information, I recommend you verify it again."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

인증

Authorization
string
header
필수

##모든 API는 Bearer Token 인증이 필요합니다##

API Key 받기:

API Key 관리 페이지를 방문하여 API Key를 받으세요

요청 헤더에 추가:

Authorization: Bearer YOUR_API_KEY

본문

application/json
model
enum<string>
기본값:gemini-3-pro-preview
필수

채팅 모델 이름

사용 가능한 옵션:
gemini-3-pro-preview
예시:

"gemini-3-pro-preview"

messages
object[]
필수

채팅 메시지 목록, 다중 턴 대화 및 멀티모달 입력 지원

Minimum array length: 1
stream
boolean

스트리밍 모드로 응답을 반환할지 여부

  • true: 스트리밍 반환, 실시간 청크로 내용 수신
  • false: 완전한 응답을 한 번에 반환
예시:

false

max_tokens
integer

생성할 최대 이미지 수, [1,15] 사이의 정수 값 지원

참고:

  • 여러 이미지를 생성하려면 프롬프트에 "2개의 다른 이미지 생성"과 같은 프롬프트를 포함하세요

  • 참조 이미지 수 + 최종 생성 이미지 수 ≤ 15개

  • 만약: 참조 이미지 수 + 프롬프트에서 요청한 이미지 수 > 15이고, 프롬프트에서 요청한 이미지 수 ≤ 매개변수 n 값이면, 최종 생성 이미지 = 15 - 참조 이미지 수

  • 각 요청은 n 값을 기준으로 선불 청구되며, 실제 청구는 생성된 이미지 수를 기준으로 합니다

필수 범위: x >= 1
예시:

2000

temperature
number

샘플링 온도, 출력의 무작위성을 제어합니다

설명:

  • 낮은 값 (예: 0.2): 더 결정적이고 집중된 출력
  • 높은 값 (예: 1.5): 더 무작위적이고 창의적인 출력
필수 범위: 0 <= x <= 2
예시:

0.7

top_p
number

Nucleus Sampling 매개변수

설명:

  • 누적 확률을 기반으로 토큰에서 샘플링을 제어합니다
  • 예를 들어, 0.9는 누적 확률 상위 90%까지의 토큰에서 선택하는 것을 의미합니다
  • 기본값: 1.0 (모든 토큰 고려)

권장 사항: temperature와 top_p를 동시에 조정하지 마세요

필수 범위: 0 <= x <= 1
예시:

0.9

top_k
integer

Top-K 샘플링 매개변수

설명:

  • 예를 들어, 10은 샘플링 시 가장 확률이 높은 상위 10개 토큰만 고려하도록 제한합니다
  • 작은 값일수록 출력이 더 집중됩니다
  • 기본값: 제한 없음
필수 범위: x >= 1
예시:

40

응답

채팅 완성이 성공적으로 생성되었습니다

id
string

채팅 완성의 고유 식별자

예시:

"chatcmpl-20251010015944503180122WJNB8Eid"

model
string

실제 사용된 모델 이름

예시:

"gemini-3-pro-preview"

object
enum<string>

응답 유형

사용 가능한 옵션:
chat.completion
예시:

"chat.completion"

created
integer

생성 타임스탬프

예시:

1760032810

choices
object[]

채팅 완성 선택지 목록

usage
object

토큰 사용 통계