ai-chat
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAI Chat — Unified LLM Gateway
AI聊天——统一LLM网关
AceDataCloud exposes two documented chat surfaces:
| Endpoint | Use For |
|---|---|
| Recommended stateful / multimodal / agentic conversations |
| Legacy conversation endpoint |
| OpenAI-compatible stateless chat completions |
| OpenAI-compatible responses API |
Setup: See authentication for token setup.
AceDataCloud提供两个已文档化的聊天接口：
| 端点 | 适用场景 |
|---|---|
| 推荐用于有状态/多模态/智能体对话 |
| 遗留对话端点 |
| 兼容OpenAI的无状态聊天补全 |
| 兼容OpenAI的响应API |
设置： 请查看身份验证了解令牌设置。
Quick Start
快速开始
Recommended: stateful conversations
推荐：有状态对话
bash
curl -X POST https://api.acedata.cloud/aichat2/conversations \
-H "Authorization: ******ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4.1","question":"Summarize the latest release notes.","stateful":true}'bash
curl -X POST https://api.acedata.cloud/aichat2/conversations \
-H "Authorization: ******ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4.1","question":"Summarize the latest release notes.","stateful":true}'OpenAI-compatible SDK
OpenAI兼容SDK
python
from openai import OpenAI
client = OpenAI(
api_key="your-token-here",
base_url="https://api.acedata.cloud/openai"
)
response = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
print(response.choices[0].message.content)python
from openai import OpenAI
client = OpenAI(
api_key="your-token-here",
base_url="https://api.acedata.cloud/openai"
)
response = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
print(response.choices[0].message.content)Currently Documented Model Families
当前已收录的模型系列
The OpenAPI specs expose a broad, fast-moving model catalog. Representative current
models include:
| Family | Current examples |
|---|---|
| OpenAI / reasoning | |
| OpenAI free-tier chat-completions | |
| Claude | |
| Gemini | |
| Grok | |
| DeepSeek | |
| Kimi | |
| GLM | |
/aichat2/conversationsmodel_groupchatgptclaudegeminigrokkimiglmdeepseekOpenAPI规范涵盖了广泛且更新迅速的模型目录。目前代表性模型包括：
| 系列 | 当前示例 |
|---|---|
| OpenAI / 推理 | |
| OpenAI免费层聊天补全 | |
| Claude | |
| Gemini | |
| Grok | |
| DeepSeek | |
| Kimi | |
| GLM | |
/aichat2/conversationsmodel_groupchatgptclaudegeminigrokkimiglmdeepseekOpenAI-Compatible Chat
兼容OpenAI的聊天接口
json
POST /openai/chat/completions
{
"model": "gpt-4.1",
"messages": [{"role": "user", "content": "Write a haiku about observability."}],
"stream": true,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"parameters": {"type": "object", "properties": {"location": {"type": "string"}}}
}
}
]
}Common parameters:
| Parameter | Type | Description |
|---|---|---|
| string | One of the documented OpenAI-compatible models |
| array | Standard OpenAI chat message list |
| number | Sampling controls |
| integer | Output cap |
| boolean | Enable SSE streaming |
| array / string-object | Function-calling controls |
| string | Processing tier ( |
json
POST /openai/chat/completions
{
"model": "gpt-4.1",
"messages": [{"role": "user", "content": "Write a haiku about observability."}],
"stream": true,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"parameters": {"type": "object", "properties": {"location": {"type": "string"}}}
}
}
]
}常用参数：
| 参数 | 类型 | 描述 |
|---|---|---|
| 字符串 | 已文档化的兼容OpenAI模型之一 |
| 数组 | 标准OpenAI聊天消息列表 |
| 数字 | 采样控制参数 |
| 整数 | 输出长度上限 |
| 布尔值 | 启用SSE流式传输 |
| 数组/字符串对象 | 函数调用控制参数 |
| 字符串 | 处理层级（ |
Stateful / Agentic Conversations
有状态/智能体对话
POST /aichat2/conversationsjson
POST /aichat2/conversations
{
"action": "chat",
"model": "claude-sonnet-4-6",
"message": [
{"type": "text", "text": "Describe this image."},
{"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
],
"stateful": true,
"allowed_skills": ["google-search"],
"allowed_mcp_servers": ["mcp-google-search"]
}Useful parameters:
| Parameter | Type | Description |
|---|---|---|
| string | |
| string | Model name |
| string | Simple text prompt |
| string or array | Multimodal content using |
| boolean | Keep conversation history server-side |
| array | Extra context documents |
| string | Preset/system prompt |
| integer | Trim retained turn history |
| array | Restrict tool-use scope |
| object | Tool-use permission policy |
| array | Return results for previously requested tool calls |
| string | Family selector ( |
| integer | Pagination for retrieval actions |
| string / boolean | Async execution |
POST /aichat2/conversationsjson
POST /aichat2/conversations
{
"action": "chat",
"model": "claude-sonnet-4-6",
"message": [
{"type": "text", "text": "Describe this image."},
{"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
],
"stateful": true,
"allowed_skills": ["google-search"],
"allowed_mcp_servers": ["mcp-google-search"]
}实用参数：
| 参数 | 类型 | 描述 |
|---|---|---|
| 字符串 | |
| 字符串 | 模型名称 |
| 字符串 | 简单文本提示 |
| 字符串或数组 | 多模态内容，支持 |
| 布尔值 | 在服务器端保留对话历史 |
| 数组 | 额外上下文文档 |
| 字符串 | 预设/系统提示词 |
| 整数 | 保留对话轮次的上限 |
| 数组 | 限制工具使用范围 |
| 对象 | 工具使用权限策略 |
| 数组 | 返回之前请求的工具调用结果 |
| 字符串 | 系列选择器（ |
| 整数 | 检索操作的分页参数 |
| 字符串/布尔值 | 异步执行设置 |
Gotchas
注意事项
- The documented OpenAI-compatible routes live under , not
/openai/*./v1/* - is the recommended stateful endpoint;
POST /aichat2/conversationsremains for legacy clients.POST /aichat/conversations - on
messagecan be multimodal (/aichat2/conversations,text,image_url); plainfile_urlstill works for simple text prompts.question - on
actionis not chat-only — it also supports/aichat2/conversations,retrieve,retrieve_batch, andupdate.delete - Free-tier model variants such as are documented on
gpt-5.5:free./openai/chat/completions
- 已文档化的兼容OpenAI路由位于下，而非
/openai/*。/v1/* - 是推荐的有状态端点；
POST /aichat2/conversations仍为遗留客户端保留。POST /aichat/conversations - 的
/aichat2/conversations参数支持多模态（message,text,image_url）；简单文本提示仍可使用file_url参数。question - 的
/aichat2/conversations参数不仅限于聊天——还支持action,retrieve,retrieve_batch, 和update操作。delete - 免费层模型变体（如）在
gpt-5.5:free接口中有文档说明。/openai/chat/completions