> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiji.cc/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat Completions

> 使用 OpenAI Chat Completions 格式调用模型，支持流式输出、工具调用和图片理解。

```text theme={null}
POST https://www.jiji.cc/v1/chat/completions
```

兼容 OpenAI Chat Completions 接口，大多数第三方应用和框架都支持这种格式。

## 基础对话

<CodeGroup>
  ```python Python theme={null}
  import os
  from openai import OpenAI

  client = OpenAI(
      base_url="https://www.jiji.cc/v1",
      api_key=os.environ["JIJI_API_KEY"],
  )

  resp = client.chat.completions.create(
      model="gpt-6.1-sol",
      messages=[
          {"role": "system", "content": "你是一个简洁的编程助手。"},
          {"role": "user", "content": "用一句话解释什么是闭包。"},
      ],
  )
  print(resp.choices[0].message.content)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://www.jiji.cc/v1",
    apiKey: process.env.JIJI_API_KEY,
  });

  const resp = await client.chat.completions.create({
    model: "gpt-6.1-sol",
    messages: [
      { role: "system", content: "你是一个简洁的编程助手。" },
      { role: "user", content: "用一句话解释什么是闭包。" },
    ],
  });
  console.log(resp.choices[0].message.content);
  ```

  ```bash cURL theme={null}
  curl https://www.jiji.cc/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $JIJI_API_KEY" \
    -d '{
      "model": "gpt-6.1-sol",
      "messages": [
        {"role": "system", "content": "你是一个简洁的编程助手。"},
        {"role": "user", "content": "用一句话解释什么是闭包。"}
      ]
    }'
  ```
</CodeGroup>

## 流式输出

设置 `stream: true`，模型会边生成边返回，适合聊天界面：

<CodeGroup>
  ```python Python theme={null}
  stream = client.chat.completions.create(
      model="gpt-6.1-sol",
      messages=[{"role": "user", "content": "写一首关于春天的短诗"}],
      stream=True,
  )
  for chunk in stream:
      if chunk.choices and chunk.choices[0].delta.content:
          print(chunk.choices[0].delta.content, end="", flush=True)
  ```

  ```javascript Node.js theme={null}
  const stream = await client.chat.completions.create({
    model: "gpt-6.1-sol",
    messages: [{ role: "user", content: "写一首关于春天的短诗" }],
    stream: true,
  });
  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
  }
  ```
</CodeGroup>

## 多轮对话

接口本身不保存历史。每次请求都要把之前的对话一起放进 `messages`：

```python Python theme={null}
messages = [{"role": "user", "content": "我叫小明"}]
resp = client.chat.completions.create(model="gpt-6.1-sol", messages=messages)

messages.append({"role": "assistant", "content": resp.choices[0].message.content})
messages.append({"role": "user", "content": "我叫什么名字？"})
resp = client.chat.completions.create(model="gpt-6.1-sol", messages=messages)
print(resp.choices[0].message.content)
```

## 工具调用

通过 `tools` 声明函数，模型会在需要时返回要调用的函数和参数，由你的代码执行后再把结果传回：

```python Python theme={null}
import json

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "查询城市的实时天气",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string", "description": "城市名"}},
            "required": ["city"],
        },
    },
}]

messages = [{"role": "user", "content": "北京今天天气怎么样？"}]
resp = client.chat.completions.create(model="gpt-6.1-sol", messages=messages, tools=tools)
msg = resp.choices[0].message

if msg.tool_calls:
    messages.append(msg)
    for call in msg.tool_calls:
        args = json.loads(call.function.arguments)
        result = {"city": args["city"], "weather": "晴", "temp": 22}  # 替换为真实查询
        messages.append({
            "role": "tool",
            "tool_call_id": call.id,
            "content": json.dumps(result, ensure_ascii=False),
        })
    resp = client.chat.completions.create(model="gpt-6.1-sol", messages=messages, tools=tools)

print(resp.choices[0].message.content)
```

## 图片理解

在 `content` 中传入图片 URL 或 Base64：

<CodeGroup>
  ```python 网络图片 theme={null}
  resp = client.chat.completions.create(
      model="gpt-6.1-sol",
      messages=[{
          "role": "user",
          "content": [
              {"type": "text", "text": "这张图片里有什么？"},
              {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
          ],
      }],
  )
  ```

  ```python 本地图片 theme={null}
  import base64

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

  resp = client.chat.completions.create(
      model="gpt-6.1-sol",
      messages=[{
          "role": "user",
          "content": [
              {"type": "text", "text": "这张图片里有什么？"},
              {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}},
          ],
      }],
  )
  ```
</CodeGroup>

## 常用参数

| 参数 | 说明 |
| - | - |
| `model` | 模型 ID，以 [模型广场](https://www.jiji.cc/extension/models) 为准 |
| `messages` | 对话消息列表 |
| `stream` | 是否流式返回 |
| `max_completion_tokens` | 最多生成的 Token 数 |
| `reasoning_effort` | 推理模型的思考强度，例如 `low`、`medium`、`high` |
| `tools` | 可供模型调用的工具列表 |
| `response_format` | 结构化输出，例如 `{"type": "json_object"}` |

<Tip>
  调用 GPT 系列的推理模型时，推荐改用 [Responses](/api/responses) 接口，对思考和工具调用的支持更完整。
</Tip>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.