メインコンテンツへスキップ
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-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}
'
{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gemini-3.1-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
  }
}

承認

Authorization
string
header
必須

##すべてのAPIにBearer Token認証が必要です##

APIキーの取得:

APIキー管理ページにアクセスしてAPIキーを取得してください

リクエストヘッダーに追加:

Authorization: Bearer YOUR_API_KEY

ボディ

application/json
model
enum<string>
デフォルト:gemini-3.1-pro-preview
必須

チャットモデル名

利用可能なオプション:
gemini-3.1-pro-preview
:

"gemini-3.1-pro-preview"

messages
object[]
必須

チャットメッセージのリスト、マルチターン対話とマルチモーダル入力をサポート

Minimum array length: 1
stream
boolean

ストリーミングモードでレスポンスを返すかどうか

  • true: ストリーミング返却、リアルタイムでチャンク単位にコンテンツを受信
  • false: 完全なレスポンスを一括で返却
:

false

max_tokens
integer

生成された応答の最大トークン数

説明:

  • 値が小さすぎると応答が切り捨てられる可能性があります
必須範囲: x >= 1
:

2000

temperature
number

サンプリング温度、出力のランダム性を制御

説明:

  • 低い値(例: 0.2): より決定論的で集中した出力
  • 高い値(例: 1.5): よりランダムで創造的な出力
必須範囲: 0 <= x <= 2
:

0.7

top_p
number

Nucleus Samplingパラメータ

説明:

  • 累積確率に基づくトークンサンプリングを制御
  • 例えば、0.9は累積確率90%までのトークンから選択することを意味します
  • デフォルト: 1.0(全トークンを考慮)

推奨: temperatureとtop_pを同時に調整しないでください

必須範囲: 0 <= x <= 1
:

0.9

top_k
integer

Top-K サンプリングパラメータ

説明:

  • 例えば、10は確率が最も高い上位10トークンのみをサンプリング対象にすることを意味します
  • 値が小さいほど出力がより集中します
  • デフォルト: 制限なし
必須範囲: x >= 1
:

40

レスポンス

チャット補完が正常に生成されました

id
string

チャット補完の一意の識別子

:

"chatcmpl-20251010015944503180122WJNB8Eid"

model
string

実際に使用されたモデル名

:

"gemini-3.1-pro-preview"

object
enum<string>

レスポンスタイプ

利用可能なオプション:
chat.completion
:

"chat.completion"

created
integer

作成タイムスタンプ

:

1760032810

choices
object[]

チャット補完選択肢のリスト

usage
object

トークン使用統計