错误信息: This is not a chat model and thus not supported in the v1/chat/completions...
🚨 错误信息
错误名称: AI_APICallError
错误信息: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?
堆栈信息: AI_APICallError: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?
at file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/dist-Cz6miDbB.js:345:11
at async postToApi (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/dist-Cz6miDbB.js:278:24)
at async OpenAICompatibleChatLanguageModel.doStream (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/dist-Cz6miDbB.js:766:48)
at async wrapStream (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:38683:32)
at async fn (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:36874:17)
at async file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:34261:19
at async _retryWithExponentialBackoff (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:34363:10)
at async streamStep (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:36842:108)
at async fn (file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:37121:5)
at async file:///Applications/Cherry%20Studio.app/Contents/Resources/app.asar/out/renderer/assets/store-C63Bp9Zw.js:34261:19
错误原因: "[undefined]"
状态码: 400
请求路径: https://www.dmxapi.cn/v1/chat/completions
请求体: {
"model": "gpt-5.2-pro",
"user": "[undefined]",
"max_tokens": "[undefined]",
"temperature": "[undefined]",
"top_p": "[undefined]",
"frequency_penalty": "[undefined]",
"presence_penalty": "[undefined]",
"response_format": "[undefined]",
"stop": "[undefined]",
"seed": "[undefined]",
"serviceTier": "[undefined]",
"reasoning_effort": "[undefined]",
"verbosity": "[undefined]",
"messages": [
{
"role": "user",
"content": "我是一个网络安全从业人员，我要每个月给我的客户做一次安全巡检（设备运行巡检、安全设备告警巡检），然后根据巡检写一份巡检报告，请帮我写一个使用chatgpt5生成报告模版的提示词"
}
],
"tools": "[undefined]",
"tool_choice": "[undefined]",
"stream": true,
"stream_options": {
"include_usage": true
}
}
响应首部: {
"cache-control": "no-cache",
"content-type": "text/event-stream",
"date": "Sun, 04 Jan 2026 08:01:33 GMT",
"server": "nginx",
"x-rixapi-request-id": "20260104160024698485938Ye5VCZ0P"
}
响应内容: {
"error": {
"message": "This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?",
"type": "rix_api_error",
"param": "model",
"code": null
}
}
数据: {
"error": {
"message": "This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?",
"type": "rix_api_error",
"param": "model",
"code": null
}
}
🤖 AI解决方案
报错分析报告
1. 错误翻译
原文:
This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?译文: 这不是一个对话模型，因此不支持在
/v1/chat/completions 接口中使用。您是否想要使用 /v1/completions 接口？2. 原因分析
根本原因: 您调用的是 OpenAI 兼容的对话模型接口 (
/v1/chat/completions)，但使用的模型 "gpt-5.2-pro" 在该平台被识别为非对话模型（即传统的"补全/续写"模型）。具体分析:
https://www.dmxapi.cn/v1/chat/completions（对话接口）"gpt-5.2-pro"（被服务端判定为非对话模型）OpenAICompatibleChatLanguageModel.doStream 方法时，API 返回了 400 错误3. 解决方案
根据 API 的错误提示，您有两种解决方案：
方案一：更换为对话接口支持的模型
如果平台有对话模型，请更换模型名称：
javascript
// 修复后的请求体（假设更换为可用的对话模型）
{
"model": "gpt-4", // 或平台支持的其他对话模型，如 gpt-3.5-turbo
"messages": [
{
"role": "user",
"content": "我是一个网络安全从业人员..."
}
],
"stream": true
// 其他参数...
}
方案二：更换为正确的接口端点
如果
"gpt-5.2-pro" 确实是您要使用的模型，请将其用于传统的补全接口：javascript
// 需要修改代码中的 API 端点
const apiUrl = 'https://www.dmxapi.cn/v1/completions'; // 注意：从 chat/completions 改为 completions// 请求体格式需要调整为补全接口的格式
const requestBody = {
"model": "gpt-5.2-pro",
"prompt": "我是一个网络安全从业人员，我要每个月给我的客户做一次安全巡检...", // 注意：从 messages 改为 prompt
"max_tokens": 1000,
"stream": true
// 补全接口的其他参数...
};
关键修改点:
/v1/chat/completions → /v1/completionsmessages 数组 → prompt 字符串4. ️ 预防措施
最佳实践建议
- 在使用 API 前，查阅平台文档确认每个模型的类型（对话模型 vs. 补全模型）
- 创建模型-接口映射表，避免混淆
``
javascript
// 在代码中添加模型类型验证
const chatModels = ['gpt-4', 'gpt-3.5-turbo', 'claude-3'];
const completionModels = ['gpt-5.2-pro', 'text-davinci-003'];
function getEndpointForModel(model) {
if (chatModels.includes(model)) {
return '/v1/chat/completions';
} else if (completionModels.includes(model)) {
return '/v1/completions';
} else {
throw new Error(未知模型类型: ${model});
}
}
`️ 开发工具推荐
API 测试工具: 使用 Postman 或 Insomnia 先测试接口，确认模型可用性
错误监控: 实现详细的错误日志记录，捕获完整的 API 响应信息
文档查阅: 定期查看平台 API 文档更新，了解模型类型的变化 ---
建议: 联系 DMXAPI 平台确认