ChatfireAPI
首页官网模型列表服务监控
关于更多
  • 充值
  • 联系客服
首页官网模型列表服务监控
关于更多
  • 充值
  • 联系客服
  1. 聊天(OpenAIChat)
  • 🔥最新公告
  • OpenAI SDK教程
  • 聊天(OpenAIChat)
    • 全模型开启Plus模式
      • 开启 联网
      • 开启 画画
      • 开启 文件问答
      • 开启 图片问答(推荐格式)
      • 开启 文件问答-支持多轮对话(推荐格式)
    • 多模态聊天(支持图片、视频)
      • 使用说明
      • OpenaiSDK用法
      • Gpt系列
      • Claude系列
      • Qwen系列
      • Internvl系列
      • Glm系列
      • Cpm系列
      • 视频解析
      • 音频解析
      • 豆包系列(混合推理,可关闭思考)
    • DeepClaude
      POST
    • 创建聊天补全(SeedEdit)
      POST
    • 图片编辑(Chat)
      POST
    • 联网模型
      POST
    • PPT助手
      POST
    • Google系列
      POST
    • 混元
      POST
    • Chat画画/视频
      POST
    • responses
      POST
  • AnthropicClaude
    • Claude(原生接口)
      POST
  • 火山引擎API
    • 使用说明
    • 豆包即梦视频生成API
      • 使用说明
      • 创建任务-seedance
      • 获取任务-seedance
    • 火山创建任务
      POST
    • 火山获取任务
      POST
  • 图像(Images)
    • 使用说明
    • 图像对象
    • 使用说明
    • SeedEdit(异步任务)
      • 人物参考
      • 创建任务
      • 获取任务
    • 图片编辑(gpt-image)
      • edits(gpt-image)
      • edits(flux)
      • 创建图片(generations)
      • 图片编辑(chat)
      • edits(gpt-image) Copy
    • Recraft(图片)
      • 生成图片(OpenaiD3)
      • 图片矢量化
      • 变高清
      • Generate Image(生成图片)
    • Flux(BFL官方接口)
      • flux-kontext
    • 即梦3.0(Seedream)
      POST
    • 即梦垫图(SeedEdit)
      POST
    • 创建图像(FLUX)
      POST
    • 创建图像(Recraftv3)
      POST
    • 创建图像(Cogview)
      POST
    • 创建图像(混元)
      POST
    • 创建图像(Kling)
      POST
    • 创建图像(StableDiffusion)
      POST
    • 创建图像
      POST
    • 创建图像变体
      POST
    • kolors(文生图/图生图)
      POST
    • 虚拟换衣(virtual-try-on)
      POST
    • flux-kontext(文生图、图生图)
      POST
    • 海螺图片
      POST
  • 视频生成(Videos)
    • 视频生成
      • 使用说明
      • 海螺视频(官方格式)
        • 获取任务
        • 创建任务(海螺视频)
      • 海螺视频(官方格式)新模型
        • 获取任务 Copy
        • 获取任务
        • 创建任务
      • 可灵AI
        • README
        • 创建任务
        • 获取任务
        • 图片上传
      • Vidu
        • 创建任务-文生视频
        • 创建任务-图生视频
        • 获取任务
        • 视频优化(Upscale)
        • 图片上传
      • 混元视频(私有化服务)
        • README
        • 创建任务
        • 获取任务
      • Runwayml-Gen3
        • 创建任务
        • 获取任务
      • Luma(在开发)
        • 创建任务
        • 获取任务
      • Pika(在开发)
        • 创建任务
        • 获取任务
    • sora
      • 官方格式
        • 创建视频
        • 查询视频
      • openai chat 格式
        • 生成视频
    • 数字人系列-对口型(lipsync)
      • 创建任务
      • 获取任务
    • Runway(官方格式)
      • 创建任务(图生视频)
      • 获取任务
    • Luma(官方格式)
      • 创建任务(图生视频)
      • 获取任务
    • 可灵API(官方格式)
      • 文生图
      • 图生图
      • 文生视频
      • 图生视频
      • 虚拟换衣(virtual-try-on)
      • 获取任务(图片)
      • 获取任务(视频)
      • 获取任务(视频)
      • 获取任务 (虚拟换衣)
    • 智谱清影(Cogvideox官方格式)
      • README
      • 创建任务
      • 获取任务
    • 可灵2.0(通用格式)
      • 创建任务
      • 获取任务
    • 即梦视频 3.0
      • 创建任务(即梦视频)
      • 获取任务(即梦视频)
  • 音频(Audio)
    • 音乐生成(Suno)
      • 使用说明
      • 生成歌词
      • 生成歌曲(灵感、自定义、续写)
      • 获取任务
    • 语音克隆(fish-tts-model)
    • 语音合成(fish-tts)
    • 创建语音
    • 创建转录
    • 创建翻译
  • 嵌入(RAG-Embeddings)
    • 嵌入对象
    • 多模态向量嵌入
    • 创建嵌入(gemini-embedding)
    • 创建嵌入
  • 重排序(RAG-Reranker)
    • README
    • 重排序
  • 对象存储+文件解析(Files)
    • 使用说明
    • 文件对象
    • 文件用途(Purpose)
      • Suno
      • 文档解析OCR(textin)
      • 文档解析OCR(moonshot/kimi)
    • 上传文件
    • 删除文件
    • 检索文件
    • 检索文件内容
    • 列出文件
  • 内容审查(Moderations)
    • README.md
    • 创建内容审核
  • 助手测试版(AssistantsBeta)待开发
    • 辅助对象
    • 辅助文件对象
    • 创建助手
    • 检索助手
    • 修改助手
    • 删除助手
    • 列出助手
    • 创建辅助文件
    • 检索助手文件
    • 删除辅助文件
    • 列出助手文件
  • 线程数(Threads)待开发
    • 线程对象
    • 创建线程
    • 检索线程
    • 修改线程
    • 删除话题
  • 留言(Messages)待开发
    • 消息对象
    • 消息文件对象
    • 创建消息
    • 检索消息
    • 修改留言
    • 列出消息
    • 检索消息文件
    • 列出消息文件
  • 运行(Runs)待开发
    • 运行对象
    • 运行步骤对象
    • 创建运行
    • 检索运行
    • 修改运行
    • 列表运行
    • 提交工具输出以运行
    • 取消运行
    • 创建线程并运行
    • 检索运行步骤
    • 列出运行步骤
  • 批量API(Batch API)待开发
    • 创建 Batch
    • 检索 Batch
    • 取消 Batch
    • 列出 Batch
    • 上传文件
  • 微调(Fine-tuning)待开发
    • 微调作业对象
    • 微调作业事件对象
    • 创建微调作业
    • 列出微调作业
    • 检索微调作业
    • 取消微调
    • 列出微调事件
  • 🔥AI 工具
    • 合合签约(Textin)
      • 去水印
      • 文件转Markdown
      • 文档图像切边增强矫正
    • 图片处理
      • 去水印(remove-watermark)
      • 去水印(remove-watermark-textin)待上线
      • 变高清(clarity)
      • 无损扩图(expand)
      • 抠图(rmbg-2.0)
      • 照片修复-待上线
      • 黑白照片上色-待上线
      • 图片矫正-待上线
    • 证件照(ID Photos)
      • 使用说明
      • 证件照生成
    • 抠图(ai-matting)
    • 变清晰(clarity)
    • 风格变换(style)
    • 图像切边增强矫正
    • 翻译助手
    • 视频转音频
    • OCR2.0
    • 图片转Markdown(image-to-markdown)
    • 图片文字识别(text-recognize)
  • 文档智能&图片处理
    • 图像水印去除(watermark-remove)
    • 文字识别(text_recognize_3d1)
    • 文档图像切边矫正(dewarp)
    • PDF转Markdown(pdf_to_markdown)
  • AI产品配置教程
    • Sider
    • 沉浸式翻译
  • 教程类
    • 视频生成模型操作指南
  • 系统API
    • ApiKey信息查询
  • Midjourney
    • 补充 - 其他参数以及回调
    • InsightFace任务提交
      • 提交swap_face任务
    • 任务提交
      • 执行动作
      • 提交Blend任务
      • 提交Describe任务
      • 提交Imagine任务
      • 提交modal
      • 提交Shorten任务
    • 任务查询
      • 查询所有任务
      • 根据ID列表查询任务
      • 分页查询任务
      • 查询任务队列
      • 取消任务
      • 指定ID获取任务
      • 获取任务图片的seed(需设置mj或niji的私信ID)
  • 未命名接口
    POST
  • 未命名接口
    POST
  1. 聊天(OpenAIChat)

混元

POST
{{YOUR_BASE_URL}}/v1/chat/completions
最后修改时间:2025-03-25 08:59:53
责任人:未设置
给定一个提示,该模型将返回一个或多个预测的完成,并且还可以返回每个位置的替代标记的概率。
为提供的提示和参数创建完成

请求参数

Authorization
在 Header 添加参数
Authorization
,其值为在 Bearer 之后拼接 Token
示例:
Authorization: Bearer ********************
Header 参数
Content-Type
string 
必需
示例值:
application/json
Accept
string 
必需
示例值:
application/json
Authorization
string 
可选
示例值:
Bearer {{YOUR_API_KEY}}
Body 参数application/json
model
string 
必需
枚举值 hunyuan-t1、hunyuan-t1-search
messages
array [object {2}] 
必需
role
string 
必需
content
string 
必需
支持 图片、文件、音频、视频url+提示词
示例
{
    "model": "hunyuan-t1", // 枚举值 hunyuan-t1、hunyuan-t1-search
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }

示例代码

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
请求示例请求示例
Shell
JavaScript
Java
Swift
curl --location -g --request POST '{{YOUR_BASE_URL}}/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "hunyuan-t1", // 枚举值 hunyuan-t1、hunyuan-t1-search
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

返回响应

🟢200成功
application/json
Body
id
string 
必需
choices
array [object {4}] 
必需
finish_reason
null 
可选
index
integer 
可选
logprobs
null 
可选
message
object 
可选
created
integer 
必需
model
string 
必需
object
string 
必需
service_tier
null 
必需
system_fingerprint
null 
必需
usage
object 
必需
completion_tokens
integer 
必需
prompt_tokens
integer 
必需
total_tokens
integer 
必需
completion_tokens_details
null 
必需
prompt_tokens_details
null 
必需
示例
{
    "id": "LpbgR5HuUuBP5k4z5DMF8j",
    "choices": [
        {
            "finish_reason": null,
            "index": 0,
            "logprobs": null,
            "message": {
                "content": "<think>\nOkay, let's see. The user sent a message that just says \"Hello!\" and the assistant responded with \"Hello!\". Now, the user is asking me to think through how to handle this interaction.\n\nFirst, I need to understand the context. It looks like a simple greeting exchange. The user might be testing if the assistant can recognize a greeting and respond appropriately. But since the conversation is already over with both saying hello, maybe the user wants to explore further possibilities or see if there's more the assistant can do.\n\nWait, the user provided the system message, the user's message, and the assistant's response. Then they asked me to describe the thought process. So perhaps they want me to analyze the interaction and explain how an assistant should handle such a case.\n\nI should consider the initial greeting. The assistant's response was correct, but maybe the user is looking for a more detailed analysis. For example, what if the user had a follow-up question? Or maybe the assistant could offer additional help beyond just saying hello.\n\nAlso, I need to check if there are any nuances I'm missing. The user might be interested in the structure of the conversation, like how the system message sets the context, how the user initiates, and how the assistant responds. Maybe discussing the importance of timely responses, tone, or providing options for further assistance.\n\nAnother angle: in some cases, after a greeting, the assistant might ask how they can assist the user further. But in this example, the assistant didn't. Maybe the user is pointing out that the response was too brief and wants suggestions on improving it.\n\nAlternatively, the user could be demonstrating a minimal interaction and wants to know what comes next. How should the assistant keep the conversation going or handle different types of follow-ups?\n\nI should also think about possible errors. What if the user's greeting wasn't clear? Or if there were typos? But in this case, it's straightforward.\n\nIn summary, the key points are: acknowledging the greeting appropriately, possibly offering further assistance, maintaining a friendly tone, and being ready to handle subsequent questions or requests. The assistant's initial response was adequate, but expanding on it could enhance the user experience.\n\n</think>The interaction between the user and assistant begins with a simple greeting exchange, which is a common way to initiate communication. Here's a breakdown of the thought process and considerations for handling such a scenario effectively:\n\n### 1. **Acknowledging the Greeting**\n   - The assistant’s response (\"Hello!\") is appropriate and polite, matching the user’s tone. It establishes a positive foundation for the conversation.\n   - **Consideration**: Ensure consistency in tone (e.g., formal vs. casual) to align with the user’s message.\n\n### 2. **Offering Further Assistance**\n   - While the initial response is sufficient, the assistant could enhance engagement by proactively offering help. For example:\n     - *“Hello! How can I assist you today?”*\n     - *“Hi there! What would you like to discuss?”*\n   - **Why?**: This invites the user to specify their needs, keeping the conversation productive rather than ending it abruptly.\n\n### 3. **Anticipating Next Steps**\n   - If this were a longer conversation, the assistant might:\n     - **Ask clarifying questions** if the user’s intent isn’t clear (e.g., *“Could you share more details?”*).\n     - **Provide options** (e.g., *“I can help with questions, advice, or brainstorming—what suits you best?”*).\n     - **Maintain context** by referencing prior messages if the discussion continues.\n\n### 4. **Handling Variations**\n   - If the user’s greeting were unusual or ambiguous (e.g., *“Hey!”* with no follow-up), the assistant might:\n     - **Use humor** (*“Hi! 😊 Long time no see—what’s up?”*).\n     - **Probe gently** (*“Hello! Are you okay, or is there something I can help with?”*).\n\n### 5. **Tone and Cultural Sensitivity**\n   - The assistant should adapt to the user’s cultural norms (e.g., formal bows in some cultures vs. casual greetings).\n   - Avoid overly enthusiastic responses if the user’s tone is reserved.\n\n### 6. **Error Handling**\n   - If the greeting contains typos or unclear language (e.g., *“Helo!”*), the assistant might:\n     - **Guess politely** (*“Hi there! Did you mean ‘Hello’?”*).\n     - **Ask for clarification** (*“Hi! I’m here—could you repeat that?”*).\n\n### Example Enhanced Interaction:\n- **User**: *“Hello!”*  \n- **Assistant**: *“Hello! 😊 How can I assist you today? Whether you need help, advice, or just a chat, I’m here!”*  \n- **User**: *“Actually, could you explain how photosynthesis works?”*  \n- **Assistant**: *“Of course! Let me break it down simply…”*\n\n### Key Takeaway:\nA successful greeting response balances politeness with proactivity, inviting the user to engage deeply while remaining flexible to handle diverse scenarios. This approach fosters smoother conversations and higher user satisfaction.\n",
                "refusal": null,
                "role": "assistant",
                "annotations": null,
                "audio": null,
                "function_call": null,
                "tool_calls": null,
                "reasoning_content": ""
            }
        }
    ],
    "created": 1742893156,
    "model": "hunyuan_t1",
    "object": "chat.completion",
    "service_tier": null,
    "system_fingerprint": null,
    "usage": {
        "completion_tokens": 2510,
        "prompt_tokens": 51,
        "total_tokens": 2561,
        "completion_tokens_details": null,
        "prompt_tokens_details": null
    }
}
修改于 2025-03-25 08:59:53
上一页
Google系列
下一页
Chat画画/视频
Built with