> ## Documentation Index > Fetch the complete documentation index at: https://docs.xhuoapi.ai/llms.txt > Use this file to discover all available pages before exploring further. # DeepSeek Chat Completion API 申请及使用 > DeepSeek AI 集成指南 - XHuoAPI DeepSeek 是一款非常强大的 AI 对话系统，只要输入提示词，就能在短短几秒内生成流畅自然的回复。DeepSeek-V3 以其出色的语言理解和生成能力在业界独树一帜，如今，DeepSeek-V3 早已在各个行业和领域广泛应用，其影响力愈发显著。无论是日常对话、创意写作，还是专业咨询、代码编程，DeepSeek-V3 都能提供令人惊叹的智能协助，极大地提高了人类的工作效率和创造力。 本文档主要介绍 DeepSeek Chat Completion API 操作的使用流程，利用它我们可以轻松使用官方 DeepSeek 的对话功能。 ## 申请流程 要使用 DeepSeek Chat Completion API，首先可以到 [DeepSeek Chat Completion API](https://api.xhuoapi.ai/documents/2d6a9bae-9a70-4aaa-bd72-28e5bd60fa67) 页面点击「Acquire」按钮，获取请求所需要的凭证： ![](https://cdn.xhuoapi.ai/nyq0xz.png) 如果你尚未登录或注册，会自动跳转到登录页面邀请您来注册和登录，登录注册之后会自动返回当前页面。 在首次申请时会有免费额度赠送，可以免费使用该 API。 ## 基本使用 接下来就可以在界面上填写对应的内容，如图所示：

在第一次使用该接口时，我们至少需要填写三个内容，一个是 `authorization`，直接在下拉列表里面选择即可。另一个参数是 `model`， `model` 就是我们选择使用 DeepSeek 官网模型类别，这里我们主要有 4 种模型，详情可以看我们提供的模型。最后一个参数是`messages`，`messages`是我们输入的提问词数组，它是一个数组，表示可以同时上传多个提问词，每个提问词包含了 `role` 和 `content`，其中 `role` 表示提问者的角色，我们提供了三种身份，分别为 `user` 、`assistant`、`system` 。另一个 `content` 就是我们提问的具体内容。 同时您可以注意到右侧有对应的调用代码生成，您可以复制代码直接运行，也可以直接点击「Try」按钮进行测试。 常用可选参数： * `max_tokens`：限制单次回复的最大 token 数。 * `temperature`：生成随机性，0-2 之间，值越大越发散。 * `n`：一次生成多少条候选回复。 * `response_format`：返回格式设置。

调用之后，我们发现返回结果如下： ```json theme={null} { "id": "chatcmpl-050bf20a-ebcd-498a-bf6e-63ee0738013b", "object": "chat.completion", "created": 1764846609, "model": "deepseek-v3.2-exp", "usage": { "prompt_tokens": 8, "completion_tokens": 11, "total_tokens": 19 }, "choices": [ { "index": 0, "message": { "content": "Hello! 😊 How can I help you today?", "role": "assistant" }, "refs": null, "logprobs": null, "finish_reason": "stop", "service_tier": null } ] } ``` 返回结果一共有多个字段，介绍如下： * `id`，生成此次对话任务的 ID，用于唯一标识此次对话任务。 * `created`，此次对话任务的创建时间信息。 * `model`，选择的 DeepSeek 官网模型。 * `choices`DeepSeek 针对提问词给于的回答信息。 * `usage `：针对本次问答对 token 的统计信息。 其中 `choices` 是包含了 DeepSeek 的回答信息，它里面的 `choices` 是 DeepSeek的回答信息，可以发现如图所示。

可以看到，`choices` 里面的 `content` 字段包含了 DeepSeek 回复的具体内容。 ## 流式响应 该接口也支持流式响应，这对网页对接十分有用，可以让网页实现逐字显示效果。 如果想流式返回响应，可以更改请求头里面的 `stream ` 参数，修改为 `true`。 修改如图所示，不过调用代码需要有对应的更改才能支持流式响应。

将 `stream` 修改为 `true` 之后，API 将逐行返回对应的 JSON 数据，在代码层面我们需要做相应的修改来获得逐行的结果。 Python 样例调用代码： ```python theme={null} import requests url = "https://api.xhuoapi.ai/v1/deepseek/chat/completions" headers = { "accept": "application/json", "authorization": "Bearer {token}", "content-type": "application/json" } payload = { "model": "deepseek-v3", "messages": [{"role":"user","content":"hello"}], "stream": True } response = requests.post(url, json=payload, headers=headers) print(response.text) ``` 输出效果如下： ```json theme={null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": "Hello", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": "!", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": "", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " 😊", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " How", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " can", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " I", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " assist", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " you", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": " today", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": "?", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null} data: {"id": "o7X27b1-2kFHot-97098d957dd1d39a-PDX", "object": "chat.completion.chunk", "created": 1755437709, "model": "deepseek-v3", "system_fingerprint": null, "choices": [{"delta": {"content": "", "role": "assistant"}, "logprobs": null, "finish_reason": "stop", "index": 0}], "usage": {"prompt_tokens": 4, "completion_tokens": 12, "total_tokens": 16, "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` 即为最新的回答内容，与上文介绍的内容一致。`choices` 是新增的回答内容，您可以根据结果来对接到您的系统中。同时流式响应的结束是根据 `data` 的内容来判断的，如果内容为 `[DONE]`，则表示流式响应回答已经全部结束。返回的 `data` 结果一共有多个字段，介绍如下： * `id`，生成此次对话任务的 ID，用于唯一标识此次对话任务。 * `model `，选择的 DeepSeek 官网模型。 * `choices`，DeepSeek 针对提问词给于的回答信息。 JavaScript 也是支持的，比如 Node.js 的流式调用代码如下： ```javascript theme={null} const options = { method: "post", headers: { "accept": "application/json", "authorization": "Bearer {token}", "content-type": "application/json" }, body: JSON.stringify({ "model": "deepseek-v3", "messages": [{"role":"user","content":"hello"}], "stream": true }) }; fetch("https://api.xhuoapi.ai/v1/deepseek/chat/completions", options) .then(response => response.json()) .then(response => console.log(response)) .catch(err => console.error(err)); ``` Java 样例代码： ```java theme={null} JSONObject jsonObject = new JSONObject(); jsonObject.put("model", "deepseek-v3"); 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.xhuoapi.ai/v1/deepseek/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()) ``` 其他语言可以另外自行改写，原理都是一样的。 ## 多轮对话 如果您想要对接多轮对话功能，需要对 `messages` 字段上传多个提问词，多个提问词的具体示例如下图所示：

Python 样例调用代码： ```python theme={null} import requests url = "https://api.xhuoapi.ai/v1/deepseek/chat/completions" headers = { "accept": "application/json", "authorization": "Bearer {token}", "content-type": "application/json" } payload = { "model": "deepseek-v3", "messages": [{"role":"user","content":"Hello"},{"role":"assistant","content":"Hi! How can I assist you today?"},{"role":"user","content":"What I say just now?"}] } response = requests.post(url, json=payload, headers=headers) print(response.text) ``` 通过上传多个提问词，就可以轻松实现多轮对话，可以得到如下回答： ```json theme={null} { "id": "as-8g3qzbsw2b", "object": "chat.completion", "created": 1755437895, "model": "deepseek-v3", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "You just said: \n\n**\"Hello\"** \n\nAnd I responded with: \n\n**\"Hi! How can I assist you today?\"** \n\nThen you followed up with: \n\n**\"What I say just now?\"** \n\nLet me know how I can help! 😊" }, "finish_reason": "stop", "flag": 0 } ], "usage": { "prompt_tokens": 22, "completion_tokens": 57, "total_tokens": 79 } } ``` 可以看到，`choices` 包含的信息与基本使用的内容是一致的，这个包含了 DeepSeek 针对多个对话进行回复的具体内容，这样就可以根据多个对话内容来回答对应的问题了。 ## 错误处理 在调用 API 时，如果遇到错误，API 会返回相应的错误代码和信息。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. ### 错误响应示例 ``` { "success": false, "error": { "code": "api_error", "message": "fetch failed" }, "trace_id": "2cf86e86-22a4-46e1-ac2f-032c0f2a4e89" } ``` ## 结论 通过本文档，您已经了解了如何使用 DeepSeek Chat Completion API 轻松实现官方 DeepSeek 的对话功能。希望本文档能帮助您更好地对接和使用该 API。如有任何问题，请随时联系我们的技术支持团队。