跳轉到主要內容
xAI Grok 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。Grok 以其獨特的幽默風格和即時網路資訊獲取能力在業界獨樹一幟，如今，Grok 已在多個創新領域嶄露頭角，其影響力正快速擴大。無論是日常對話、創意寫作，還是技術分析、程式碼除錯，Grok 都能提供富有洞察力的智能協助，為用戶的決策和創作帶來全新維度的支持。 本文檔主要介紹 Grok Chat Completion API 操作的使用流程，利用它我們可以輕鬆使用官方 Grok 的對話功能。

​
申請流程

要使用 Grok Chat Completion API，首先可以到 Grok 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：

在第一次使用該介面時，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 Grok 官網模型類別，這裡我們主要有 8 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。 常用可選參數：
  • max_tokens：限制單次回覆的最大 token 數。
  • temperature：生成隨機性，0-2 之間，值越大越發散。
  • n：一次生成多少條候選回覆。

調用之後，我們發現返回結果如下： 
{
  "id": "foaicmpl-13936918-cb99-49e1-b94c-bde98b482ed4",
  "model": "grok-3",
  "object": "chat.completion",
  "created": 1755839683,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Yo! What's up? 😎 Ready to dive into whatever you're pondering about today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 20,
    "total_tokens": 28,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}
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 Grok 官網模型。
  • choices，Grok 針對提問詞給予的回答資訊。
  • usage ：針對本次問答對 token 的統計資訊。
其中 choices 是包含了 Grok 的回答資訊，它裡面的 choices 是 Grok回答的具體資訊，可以發現如圖所示。

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

​
流式響應

該介面也支持流式響應，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/grok/chat/completions"

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

payload = {
    "model": "grok-3",
    "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": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "Yo, "}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "what"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data:
{"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "'s g"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "ood?"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": " Rea"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "dy t"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "o di"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "ve i"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "nto "}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "what"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "ever"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": " you"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "'re "}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "pond"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "erin"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "g ab"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "out "}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "toda"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {"content": "y?"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} 

data: {"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": null, "choices": [{"delta": {}, "logprobs": null, "finish_reason": "stop", "index": 0}], "usage": {"prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0, "prompt_tokens_details": {"cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0}, "completion_tokens_details": {"text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0}, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null}} 

data:
{"id": "foaicmpl-503ab14f-3f22-46ab-9f91-3fb44773be38", "object": "chat.completion.chunk", "created": 1755839790, "model": "grok-3", "system_fingerprint": "", "choices": [], "usage": {"prompt_tokens": 8, "completion_tokens": 18, "total_tokens": 26, "prompt_tokens_details": {"cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0}, "completion_tokens_details": {"text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0}, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null}} 

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 Grok 官網模型。
  • choices，Grok 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": "grok-3",
    "messages": [{"role":"user","content":"Hello"}],
    "stream": true
  })
};

fetch("https://api.acedata.cloud/grok/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", "grok-3");
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/grok/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/grok/chat/completions"

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

payload = {
    "model": "grok-3",
    "messages": [{"role":"user","content":"Hello"},{"role":"assistant","content":"What model are you?"},{"role":"user","content":"What did I just say?"}]
}

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": "foaicmpl-984ebc53-76b3-4d33-b0e8-0307ab4965af",
  "model": "grok-3",
  "object": "chat.completion",
  "created": 1755839996,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "You said, \"Hello.\""
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 27,
    "completion_tokens": 6,
    "total_tokens": 33,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}
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 Grok 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 OpenAI Chat Completion API 輕鬆實現官方 OpenAI ChatGPT 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。