靠谱One API 文档

1快速开始

2API 地址与认证

所有接口均通过 HTTP Header 中的 Authorization: Bearer 进行认证。请求格式为 JSON，需设置 Content-Type: application/json。

支持的 API 格式

3对话补全接口

核心接口，兼容 OpenAI /v1/chat/completions，支持所有已接入模型。

请求地址

POST https://nuo.zhongzheng.xin/v1/chat/completions

请求参数

消息角色 (role)

基本请求示例

bashcurl https://nuo.zhongzheng.xin/v1/chat/completions \
  -H "Authorization: Bearer sk-你的令牌" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "你是一个有帮助的助手"},
      {"role": "user", "content": "你好！"}
    ],
    "temperature": 0.7
  }'

响应格式

json{
  "id": "chatcmpl-xxxxx",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "你好！有什么我可以帮助你的吗？"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 15,
    "total_tokens": 35
  }
}

4流式输出 (Streaming)

设置 "stream": true，接口将以 SSE (Server-Sent Events) 格式逐步返回内容，适合实时显示打字效果。

请求

bashcurl https://nuo.zhongzheng.xin/v1/chat/completions \
  -H "Authorization: Bearer sk-你的令牌" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "写一首诗"}],
    "stream": true
  }'

SSE 响应格式

ssedata: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"春"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"风"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"吹"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Python 流式示例

pythonfrom openai import OpenAI

client = OpenAI(api_key="sk-你的令牌", base_url="https://nuo.zhongzheng.xin/v1")

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "讲个笑话"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

5Anthropic 原生格式

除 OpenAI 格式外，还支持 Anthropic 原生 /v1/messages 接口，适合已有 Claude 集成的项目。

请求

bashcurl https://nuo.zhongzheng.xin/v1/messages \
  -H "x-api-key: sk-你的令牌" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "你好！"}
    ]
  }'

Python (Anthropic SDK)

pythonimport anthropic

client = anthropic.Anthropic(
    api_key="sk-你的令牌",
    base_url="https://nuo.zhongzheng.xin"
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "你好！"}]
)
print(message.content[0].text)

6模型列表接口

实时查询当前可用的所有模型。

bashGET https://nuo.zhongzheng.xin/v1/models
Authorization: Bearer sk-你的令牌

响应

json{
  "data": [
    {"id": "gpt-4o", "object": "model", "owned_by": "openai"},
    {"id": "claude-sonnet-4-6", "object": "model", "owned_by": "anthropic"},
    {"id": "deepseek-v4-pro", "object": "model", "owned_by": "deepseek"},
    ...
  ]
}

7可用模型

已接入以下模型系列，持续更新中。系统自动根据模型名称路由到对应上游，无需手动选择。

模型选择建议

8多模态 (图片输入)

支持 GPT-4o、Claude、Gemini 等模型的多模态能力，可以分析图片内容。

图片 URL 方式

pythonresponse = client.chat.completions.create(
    model="gpt-4o",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "描述这张图片"},
            {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
        ]
    }]
)

Base64 方式

pythonimport base64

with open("image.png", "rb") as f:
    b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "图片里有什么？"},
            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}}
        ]
    }]
)

9Function Calling (工具调用)

支持 GPT 和 Claude 系列模型的 Function Calling，让 AI 调用你定义的函数。

定义工具

pythontools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "获取指定城市的天气",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string", "description": "城市名"}
            },
            "required": ["city"]
        }
    }
}]

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "北京今天天气怎么样？"}],
    tools=tools,
    tool_choice="auto"
)

# 检查是否需要调用工具
if response.choices[0].message.tool_calls:
    tool_call = response.choices[0].message.tool_calls[0]
    print(f"调用函数: {tool_call.function.name}")
    print(f"参数: {tool_call.function.arguments}")

返回工具结果

python# 模拟函数执行结果
weather_result = '{"temperature": 25, "condition": "晴"}'

# 将结果送回模型
response2 = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "北京今天天气怎么样？"},
        response.choices[0].message,
        {
            "role": "tool",
            "tool_call_id": tool_call.id,
            "content": weather_result
        }
    ],
    tools=tools
)
print(response2.choices[0].message.content)

10客户端接入指南

靠谱One 兼容 OpenAI API，可直接接入各类第三方客户端。

11代码示例

pythonfrom openai import OpenAI

client = OpenAI(
    api_key="sk-你的令牌",
    base_url="https://nuo.zhongzheng.xin/v1"
)

# 基本对话
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "你是一个有帮助的助手"},
        {"role": "user", "content": "解释一下量子计算"}
    ],
    temperature=0.7
)
print(response.choices[0].message.content)
print(f"Token 用量: {response.usage.total_tokens}")

# 多轮对话
messages = [
    {"role": "system", "content": "你是一个编程助手"}
]
messages.append({"role": "user", "content": "Python 如何读取文件？"})
response = client.chat.completions.create(model="gpt-4o-mini", messages=messages)
messages.append({"role": "assistant", "content": response.choices[0].message.content})
messages.append({"role": "user", "content": "如何逐行读取？"})
response2 = client.chat.completions.create(model="gpt-4o-mini", messages=messages)

javascriptimport OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-你的令牌",
  baseURL: "https://nuo.zhongzheng.xin/v1",
});

// 基本对话
const res = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "你是一个有帮助的助手" },
    { role: "user", content: "解释一下量子计算" },
  ],
  temperature: 0.7,
});
console.log(res.choices[0].message.content);
console.log(`Token 用量: ${res.usage.total_tokens}`);

// 流式输出
const stream = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "写一首诗" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

bash# 基本对话
curl https://nuo.zhongzheng.xin/v1/chat/completions \
  -H "Authorization: Bearer sk-你的令牌" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "你好！"}]
  }'

# 流式输出
curl https://nuo.zhongzheng.xin/v1/chat/completions \
  -H "Authorization: Bearer sk-你的令牌" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "你好！"}],
    "stream": true
  }'

# 查询模型列表
curl https://nuo.zhongzheng.xin/v1/models \
  -H "Authorization: Bearer sk-你的令牌"

java// 使用 OkHttp 调用
OkHttpClient client = new OkHttpClient();

String json = """
{
  "model": "gpt-4o-mini",
  "messages": [
    {"role": "user", "content": "你好！"}
  ]
}
""";

RequestBody body = RequestBody.create(json,
    MediaType.parse("application/json"));

Request request = new Request.Builder()
    .url("https://nuo.zhongzheng.xin/v1/chat/completions")
    .addHeader("Authorization", "Bearer sk-你的令牌")
    .post(body)
    .build();

try (Response response = client.newCall(request).execute()) {
    System.out.println(response.body().string());
}

12令牌管理

每个用户可创建多个 API 令牌，用于不同场景隔离。

13速率限制与配额

速率限制

额度计费

14错误码参考

错误响应格式

json{
  "error": {
    "message": "Invalid API key",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

推荐重试策略

pythonimport time

def call_with_retry(client, model, messages, max_retries=3):
    for i in range(max_retries):
        try:
            return client.chat.completions.create(
                model=model, messages=messages
            )
        except Exception as e:
            if "429" in str(e) and i < max_retries - 1:
                wait = (2 ** i) + 1  # 指数退避: 2s, 5s, 11s
                print(f"触发限流，{wait}s 后重试...")
                time.sleep(wait)
            else:
                raise

?常见问题