跳轉到主要內容
Kimi 是一款非常強大的 AI 對話系統，只要輸入提示詞，就能在短短幾秒內生成流暢自然的回覆。Kimi 都能提供令人驚嘆的智能協助，極大地提高了人類的工作效率和創造力。 本文檔主要介紹 Kimi Chat Completion API 操作的使用流程，利用它我們可以輕鬆使用官方 Kimi 的對話功能。

​
申請流程

要使用 Gemini Chat Completion API，首先可以到 Kimi Chat Completion API 頁面點擊「Acquire」按鈕，獲取請求所需要的憑證： 如果你尚未登入或註冊，會自動跳轉到登入頁面邀請您來註冊和登入，登入註冊之後會自動返回當前頁面。 在首次申請時會有免費額度贈送，可以免費使用該 API。

​
基本使用

接下來就可以在介面上填寫對應的內容，如圖所示：

在第一次使用該接口時，我們至少需要填寫三個內容，一個是 authorization，直接在下拉列表裡面選擇即可。另一個參數是 model， model 就是我們選擇使用 Kimi 官網模型類別，這裡我們主要有 7 種模型，詳情可以看我們提供的模型。最後一個參數是messages，messages是我們輸入的提問詞數組，它是一個數組，表示可以同時上傳多個提問詞，每個提問詞包含了 role 和 content，其中 role 表示提問者的角色，我們提供了三種身份，分別為 user 、assistant、system 。另一個 content 就是我們提問的具體內容。 同時您可以注意到右側有對應的調用代碼生成，您可以複製代碼直接運行，也可以直接點擊「Try」按鈕進行測試。

調用之後，我們發現返回結果如下： 
{
  "id": "chatcmpl-b5d9e1b799c137e3",
  "object": "chat.completion",
  "created": 1770991864,
  "model": "kimi-k2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": " Hello! How can I help you today?",
        "refusal": null,
        "reasoning_content": " The user has simply said \"Hello\". This is a straightforward greeting. I should respond in a friendly, helpful manner while being ready to assist with whatever they need next. Since there's no specific question or task yet, I'll acknowledge their greeting and ask how I can help.\n\nI should keep it:\n- Friendly and welcoming\n- Professional but warm\n- Open-ended to invite them to share what they need help with\n- Concise but not too brief\n\nPossible responses:\n1. \"Hello! How can I help you today?\"\n2. \"Hi there! What can I do for you?\"\n3. \"Hello! I'm ready to assist. What would you like to know or work on?\"\n4. \"Hey! Great to meet you. How can I be of service?\"\n\nI'll go with something warm and professional that invites them to share what they need. ",
        "reasoning": " The user has simply said \"Hello\". This is a straightforward greeting. I should respond in a friendly, helpful manner while being ready to assist with whatever they need next. Since there's no specific question or task yet, I'll acknowledge their greeting and ask how I can help.\n\nI should keep it:\n- Friendly and welcoming\n- Professional but warm\n- Open-ended to invite them to share what they need help with\n- Concise but not too brief\n\nPossible responses:\n1. \"Hello! How can I help you today?\"\n2. \"Hi there! What can I do for you?\"\n3. \"Hello! I'm ready to assist. What would you like to know or work on?\"\n4. \"Hey! Great to meet you. How can I be of service?\"\n\nI'll go with something warm and professional that invites them to share what they need. ",
        "tool_calls": []
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 184,
    "total_tokens": 193,
    "prompt_tokens_details": {
      "cached_tokens_details": {}
    },
    "completion_tokens_details": {}
  }
}
返回結果一共有多個字段，介紹如下：
  • id，生成此次對話任務的 ID，用於唯一標識此次對話任務。
  • model ，選擇的 Kimi 官網模型。
  • choicesKimi 針對提問詞給予的回答信息。
  • usage ：針對本次問答對 token 的統計信息。
其中 choices 是包含了 Kimi 的回答信息，它裡面的 choices 是 Kimi回答的具體信息，可以發現如圖所示。

可以看到，choices 裡面的 content 字段包含了 Gemini 回覆的具體內容。

​
流式響應

該接口也支持流式響應，這對網頁對接十分有用，可以讓網頁實現逐字顯示效果。 如果想流式返回響應，可以更改請求頭裡面的 stream 參數，修改為 true。 修改如圖所示，不過調用代碼需要有對應的更改才能支持流式響應。

將 stream 修改為 true 之後，API 將逐行返回對應的 JSON 數據，在代碼層面我們需要做相應的修改來獲得逐行的結果。 Python 樣例調用代碼： 
import requests

url = "https://api.acedata.cloud/kimi/chat/completions"

headers = {
    "accept": "application/json",
    "authorization": "Bearer {token}",
    "content-type": "application/json"
}

payload = {
    "model": "kimi-k2.5",
    "messages": [{"role":"user","content":"Hello"}],
    "stream": True
}

response = requests.post(url, json=payload, headers=headers)
print(response.text)
輸出效果如下： 
data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"content": "", "role": "assistant"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 這", "reasoning": " 這"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 使用者說了「你好」。這是一個簡單的問候", "reasoning": " 使用者說了「你好」。這是一個簡單的問候"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": "。我應該以友好、熱情的方式回應", "reasoning": "。我應該以友好、熱情的方式回應"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": "。由於這是對話的開始，", "reasoning": "。由於這是對話的開始，"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 我應該問我今天能如何幫助他們。\n\n", "reasoning": " 我應該問我今天能如何幫助他們。\n\n"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": "讓我來構思一個回應：\n- 確認這個", "reasoning": "讓我來構思一個回應：\n- 確認這個"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 問候\n- 提供協助\n- 保持溫暖", "reasoning": " 問候\n- 提供協助\n- 保持溫暖"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 和專業\n\n像這樣：\"你好！我", "reasoning": " 和專業\n\n像這樣：\"你好！我"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 能如何幫助你今天？\"或\"嗨，", "reasoning": " 能如何幫助你今天？\"或\"嗨，"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": "! 我能為你做什麼？\"\n\n其實", "reasoning": "! 我能為你做什麼？\"\n\n其實"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": "，根據上下文，這似乎是", "reasoning": "，根據上下文，這似乎是"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 一個一般的對話開場白。我會保持簡單並", "reasoning": " 一個一般的對話開場白。我會保持簡單並"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"reasoning_content": " 開放式以鼓勵他們分享他們的需求", "reasoning": " 開放式以鼓勵他們分享他們的需求"}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"content": " 你好！我能幫助", "reasoning_content": " 幫助。 ", "reasoning": " 幫助。 "}, "logprobs": null, "finish_reason": null}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [{"index": 0, "delta": {"content": " 你今天嗎？"}, "logprobs": null, "finish_reason": "stop"}], "usage": null}

data: {"id": "chatcmpl-952dd5e75583c4d1", "object": "chat.completion.chunk", "created": 1770992031, "model": "kimi-k2.5", "system_fingerprint": null, "choices": [], "usage": {"prompt_tokens": 9, "completion_tokens": 135, "total_tokens": 144, "prompt_tokens_details": {"cached_tokens_details": {}}, "completion_tokens_details": {}}}

data: [DONE]
可以看到，响应里面有许多 data ，data 里面的 choices 即為最新的回答內容，與上文介紹的內容一致。choices 是新增的回答內容，您可以根據結果來對接到您的系統中。同時流式響應的結束是根據 data 的內容來判斷的，如果內容為 [DONE]，則表示流式響應回答已經全部結束。返回的 data 結果一共有多個字段，介紹如下：
  • id，生成此次對話任務的 ID，用於唯一標識此次對話任務。
  • model ，選擇的 Kimi 官網模型。
  • choices，Kimi 針對提問詞給予的回答信息。
JavaScript 也是支持的，比如 Node.js 的流式調用代碼如下： 
const options = {
  method: "post",
  headers: {
    "accept": "application/json",
    "authorization": "Bearer {token}",
    "content-type": "application/json"
  },
  body: JSON.stringify({
    "model": "kimi-k2.5",
    "messages": [{"role":"user","content":"Hello"}],
    "stream": true
  })
};

fetch("https://api.acedata.cloud/kimi/chat/completions", options)
  .then(response => response.json())
  .then(response => console.log(response))
  .catch(err => console.error(err));
Java 樣例代碼： 
JSONObject jsonObject = new JSONObject();
jsonObject.put("model", "kimi-k2.5");
jsonObject.put("messages", [{"role":"user","content":"Hello"}]);
jsonObject.put("stream", true);
MediaType mediaType = "application/json; charset=utf-8".toMediaType();
RequestBody body = jsonObject.toString().toRequestBody(mediaType);
Request request = new Request.Builder()
  .url("https://api.acedata.cloud/kimi/chat/completions")
  .post(body)
  .addHeader("accept", "application/json")
  .addHeader("authorization", "Bearer {token}")
  .addHeader("content-type", "application/json")
  .build();

OkHttpClient client = new OkHttpClient();
Response response = client.newCall(request).execute();
System.out.print(response.body!!.string())
其他語言可以另外自行改寫，原理都是一樣的。

​
多輪對話

如果您想要對接多輪對話功能，需要對 messages 字段上傳多個提問詞，多個提問詞的具體示例如下圖所示：

Python 樣例調用代碼： 
import requests

url = "https://api.acedata.cloud/kimi/chat/completions"

headers = {
    "accept": "application/json",
    "authorization": "Bearer {token}",
    "content-type": "application/json"
}

payload = {
    "model": "kimi-k2.5",
    "messages": [{"role":"assistant","content":"Hello! How can I help you today?"},{"role":"user","content":"What model are you?"}]
}

response = requests.post(url, json=payload, headers=headers)
print(response.text)
透過上傳多個提問詞，就可以輕鬆實現多輪對話，可以得到如下回答： 
{
  "id": "chatcmpl-81e5f161ea077f5e",
  "object": "chat.completion",
  "created": 1770992310,
  "model": "kimi-k2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": " I'm Kimi, an AI assistant made by Moonshot AI. I'm from the **K2.5** series.",
        "refusal": null,
        "reasoning_content": " The user is asking \"What model are you?\" They want to know which AI model I am.\n\n I should identify myself as Kimi, an AI assistant made by Moonshot AI. I should mention that I'm Kimi from the K2.5 series specifically, as that's the model currently deployed.\n\n Key points:\n - I am Kimi\n - Made by Moonshot AI\n - Currently Kimi K2.5 (or just say I'm part of the K2.5 series)\n - I should be helpful and direct\n\n I should not:\n - Claim to be a different model (like GPT-4, Gemini, etc.)\n - Be evasive about my identity\n - Make up version numbers that aren't correct\n\n The current model identity is Kimi K2.5 (though sometimes the exact series designation might vary by deployment, but K2.5 is the current flagship). I'll identify myself as Kimi, an AI assistant by Moonshot AI, and mention I'm from the K2.5 series.\n\n Simple, direct, accurate. ",
        "reasoning": " The user is asking \"What model are you?\" They want to know which AI model I am.\n\n I should identify myself as Kimi, an AI assistant made by Moonshot AI. I should mention that I'm Kimi from the K2.5 series specifically, as that's the model currently deployed.\n\n Key points:\n - I am Kimi\n - Made by Moonshot AI\n - Currently Kimi K2.5 (or just say I'm part of the K2.5 series)\n - I should be helpful and direct\n\n I should not:\n - Claim to be a different model (like GPT-4, Gemini, etc.)\n - Be evasive about my identity\n - Make up version numbers that aren't correct\n\n The current model identity is Kimi K2.5 (though sometimes the exact series designation might vary by deployment, but K2.5 is the current flagship). I'll identify myself as Kimi, an AI assistant by Moonshot AI, and mention I'm from the K2.5 series.\n\n Simple, direct, accurate. ",
        "tool_calls": []
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 235,
    "total_tokens": 263,
    "prompt_tokens_details": {
      "cached_tokens_details": {}
    },
    "completion_tokens_details": {}
  }
}
可以看到，choices 包含的信息與基本使用的內容是一致的，這個包含了 Kimi 針對多個對話進行回覆的具體內容，這樣就可以根據多個對話內容來回答對應的問題了。

​
錯誤處理

在調用 API 時，如果遇到錯誤，API 會返回相應的錯誤代碼和信息。例如：
  • 400 token_mismatched：Bad request, possibly due to missing or invalid parameters.
  • 400 api_not_implemented：Bad request, possibly due to missing or invalid parameters.
  • 401 invalid_token：Unauthorized, invalid or missing authorization token.
  • 429 too_many_requests：Too many requests, you have exceeded the rate limit.
  • 500 api_error：Internal server error, something went wrong on the server.

​
錯誤響應示例

{
  "success": false,
  "error": {
    "code": "api_error",
    "message": "fetch failed"
  },
  "trace_id": "2cf86e86-22a4-46e1-ac2f-032c0f2a4e89"
}

​
結論

透過本文檔，您已經了解了如何使用 Gemini Chat Completion API 輕鬆實現官方 Gemini 的對話功能。希望本文檔能幫助您更好地對接和使用該 API。如有任何問題，請隨時聯繫我們的技術支持團隊。