比官方便宜一半以上！OpenAI Responses API 教程

可以看到，响应里面有许多 data ，data 里面的 delta 即为最新的回答内容，与上文介绍的内容一致。delta 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 type 的内容为 response.completed，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：

item_id，生成此次对话任务的 ID，用于唯一标识此次对话任务。
type，生成此次对话 Responses 任务的类型。
model，选择的 OpenAI ChatGPT 官网模型。
delta，ChatGPT 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 const options = { method: "post", headers: { accept: "application/json", authorization: "Bearer b82d32f570bc434d9ba9923aa0e7dce0", "content-type": "application/json", }, body: JSON.stringify({ model: "gpt-4.1", input: [{ role: "user", content: "Hello" }], stream: true, }), };

fetch("https://api.acedata.cloud/openai/responses", options) .then((response) => response.json()) .then((response) => console.log(response)) .catch((err) => console.error(err)); ```



Java 样例代码：



```java JSONObject jsonObject = new JSONObject(); jsonObject.put("model", "gpt-4.1"); jsonObject.put("input", [{"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/openai/responses") .post(body) .addHeader("accept", "application/json") .addHeader("authorization", "Bearer b82d32f570bc434d9ba9923aa0e7dce0") .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 input 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 import requests

url = "https://api.acedata.cloud/openai/responses"

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

payload = { "model": "gpt-4.1", "input": [{"role":"user","content":"Hello"},{"role":"assistant","content":"Hello! How can I help you today? 😊"},{"role":"user","content":"What did I just say?"}] }

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 { "id": "resp_68a989c03c508191a1dd82ce2e37e88a0932a4328c0a5d5b", "object": "response", "created_at": 1755941312, "status": "completed", "background": false, "content_filters": null, "error": null, "incomplete_details": null, "instructions": null, "max_output_tokens": null, "max_tool_calls": null, "model": "gpt-4.1", "output": [ { "id": "msg_68a989c092e4819189821a9eb8247e1e0932a4328c0a5d5b", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "text": "You just said \"Hello.\" \n\nWould you like to continue the conversation or ask a question?" } ], "role": "assistant" } ], "parallel_tool_calls": true, "previous_response_id": null, "prompt_cache_key": null, "reasoning": { "effort": null, "summary": null }, "safety_identifier": null, "service_tier": "default", "store": true, "temperature": 1, "text": { "format": { "type": "text" } }, "tool_choice": "auto", "tools": [], "top_p": 1, "truncation": "disabled", "usage": { "input_tokens": 32, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens": 20, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 52 }, "user": null, "metadata": {} }

可以看到，output 包含的信息与基本使用的内容是一致的，这个包含了 ChatGPT 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。

视觉模型
gpt-4o 是 OpenAI 开发的多模态大型语言模型,它在 GPT-4 的基础上增加了视觉理解能力。这个模型可以同时处理文本和图像输入,实现了跨模态的理解和生成。

使用 gpt-4o 模型的文本处理是与上文的基本使用内容一致的，下面将简要介绍一下如果使用模型的图像处理能力。

使用 gpt-4o 模型的图像处理能力主要是通过在原有的 content 内容基础上添加一个 type 字段，通过该字段可以知道上传的是文本还是图片，从而使用 gpt-4o 模型的图像处理能力，下面主要讲述采用 Curl 和 Python 俩种方式来调用该功能。

Curl 脚本方式
curl -X POST 'https://api.acedata.cloud/openai/responses' \ -H 'accept: application/json' \ -H 'authorization: Bearer {token}' \ -H 'content-type: application/json' \ -d '{ "model": "gpt-4.1", "input": [ { "role": "user", "content": [ {"type": "input_text", "text": "what is in this image?"}, { "type": "input_image", "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } ] } ] }'

Python 脚本方式


```python import requests

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

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

payload = { "model": "gpt-4.1", "input": [ { "role": "user", "content": [ {"type": "input_text", "text": "what is in this image?"}, { "type": "input_image", "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } ] } ] }

response = requests.post(url, json=payload, headers=headers) print(response.text) ```



然后可以得到下面的结果，结果里面的字段信息是与上文一致的，具体的如下：

json { "id": "resp_68a98c1bb784819e9b9f622007a2d37602483949012d2193", "object": "response", "created_at": 1755941915, "status": "completed", "background": false, "content_filters": null, "error": null, "incomplete_details": null, "instructions": null, "max_output_tokens": null, "max_tool_calls": null, "model": "gpt-4.1", "output": [ { "id": "msg_68a98c1dd030819e97fb71e6ee33f5a902483949012d2193", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "text": "This image shows a scenic path, possibly a boardwalk, running through a lush green field or meadow. The sky above is bright blue with some white clouds, and there are green trees and bushes in the background. It looks like a peaceful nature scene, possibly in a park, wetland, or prairie area. The image conveys a sense of tranquility and natural beauty." } ], "role": "assistant" } ], "parallel_tool_calls": true, "previous_response_id": null, "prompt_cache_key": null, "reasoning": { "effort": null, "summary": null }, "safety_identifier": null, "service_tier": "default", "store": true, "temperature": 1, "text": { "format": { "type": "text" } }, "tool_choice": "auto", "tools": [], "top_p": 1, "truncation": "disabled", "usage": { "input_tokens": 1118, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens": 75, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 1193 }, "user": null, "metadata": {} }

可以看到回答的内容是基于图片进行回答的，因此通过上述俩种方式可以轻松使用 gpt-4.1 模型的文本和图像处理能力。

除了，gpt-4.1，还有一个更低成本的模型，叫做 gpt-4o-mini。gpt-4o-mini 是 OpenAI 开发的最新一代大型语言模型，它不仅响应速度快，同时价格也更便宜，也支持多模态。vision 功能的使用可参考上文 gpt-4.1 模型的使用的内容。

文件处理模型的创建
请求样例：

json { "model": "gpt-4.1", "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "what is in this file?" }, { "type": "input_file", "file_url": "https://www.berkshirehathaway.com/letters/2024ltr.pdf" } ] } ] }

样例结果：

json { "id": "resp_68a98d7bb57c819ba25424f5f50a29a300a1af2af822e88a", "object": "response", "created_at": 1755942267, "status": "completed", "background": false, "content_filters": null, "error": null, "incomplete_details": null, "instructions": null, "max_output_tokens": null, "max_tool_calls": null, "model": "gpt-4.1", "output": [ { "id": "msg_68a98d7d9b80819b9b0f09b7bcd00bf900a1af2af822e88a", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "text": "The file you posted contains the **2024 annual letter to shareholders from Berkshire Hathaway Inc.**, written by Warren E. Buffett, Chairman of the Board. This document is a comprehensive communication that is typically included in Berkshire's annual report to shareholders.\n\n### What's Inside the File:\n\n#### 1. **Chairman's Letter to Shareholders**\n - **Introduction & Philosophy:** Warren Buffett discusses the purpose of the annual report, Berkshire Hathaway’s communication style, and his philosophy for transparency and candid discussion of both successes and failures.\n - **Discussion of Mistakes:** He talks openly about the mistakes made in capital allocation and personnel decisions, emphasizing the importance of admitting errors and acting promptly to correct them.\n - **Succession Comments:** Buffett references his eventual retirement, and that Greg Abel will succeed him as CEO and writer of these letters.\n - **Anecdotal Story:** The story of Pete Liegl, founder of Forest River (an RV manufacturer acquired by Berkshire), is told to illustrate management philosophy and business decision-making.\n\n#### 2. **2024 Business and Financial Performance**\n - **Key Results:** Summary of how Berkshire performed financially in 2024 vs. 2023, including operating earnings breakdown by business segments such as insurance, BNSF railroad, and energy.\n - **Insurance Business:** GEICO and the property-casualty insurance division had a standout year, with commentary on the industry and how Berkshire approaches insurance risk, pricing, and investment of insurance \"float.\"\n - **Investments:** Discussion on Berkshire’s strategy of owning both full businesses and partial stakes (marketable securities) in large companies (e.g., Apple, American Express, Coca-Cola), and its deployment of cash.\n - **Taxes:** Reference to Berkshire breaking records in corporate tax payments ($26.8 billion to the IRS in 2024).\n\n#### 3. **Long-term Philosophy & Capitalism Commentary**\n - **On Equities:** Buffett explains why Berkshire prioritizes ownership of businesses (equities) over cash or bonds, and why the company favors long-term investments.\n - **On Capitalism:** There’s a reflection on America’s growth, the role of capitalism, savings, and capital allocation in the nation’s success, and a nod to the importance of maintaining a stable currency.\n\n#### 4. **Japanese Investments**\n - **Update on Japanese Holdings:** Berkshire’s growing investments in five Japanese trading companies, and the positive view of their management and governance.\n\n#### 5. **Berkshire Hathaway Annual Meeting**\n - **Annual Gathering Info:** Details about the annual meeting in Omaha, including social events, book sales, and charitable initiatives related to the meeting.\n - **Personal Stories:** Personal anecdotes involving Buffett’s family, (including his sister Bertie), to add a human touch to the letter.\n\n#### 6. **Performance Tables**\n - **Berkshire vs S&P 500 (1965-2024):** Two detailed tables showing annual percentage change in Berkshire’s share price vs. total return for the S&P 500, as well as long-term compounded and overall gains.\n\n---\n\n### In Summary\n\nThis file is the **2024 Berkshire Hathaway annual letter to shareholders**, primarily written by Warren Buffett. It covers business performance, management philosophy, investment strategy, earnings and taxes, insurance operations, significant holdings, capital allocation, succession updates, and more. Tables show a remarkable outperformance of Berkshire Hathaway vs. the S&P 500 over nearly six decades – a central point of pride in the letter.\n\nIf you want specifics from any particular section, let me know!" } ], "role": "assistant" } ], "parallel_tool_calls": true, "previous_response_id": null, "prompt_cache_key": null, "reasoning": { "effort": null, "summary": null }, "safety_identifier": null, "service_tier": "default", "store": true, "temperature": 1, "text": { "format": { "type": "text" } }, "tool_choice": "auto", "tools": [], "top_p": 1, "truncation": "disabled", "usage": { "input_tokens": 8438, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens": 731, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 9169 }, "user": null, "metadata": {} }

可以看到，我们对输入的文件也进行了处理文件，结果与上文类似。

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 OpenAI Responses API 轻松实现官方 OpenAI 的创建 Responses 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。