GLM-5.3 与 GLM-5.3-Flash 上线：智谱编程旗舰与多模态轻量版

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.apiyi.com/v1"
)

# 旗舰：长程编程任务
response = client.chat.completions.create(
    model="glm-5.3",
    reasoning_effort="high",
    messages=[
        {"role": "system", "content": "你是一名资深软件工程师，擅长仓库级重构与安全审计。"},
        {"role": "user", "content": "请审计这个仓库的鉴权模块，列出可被利用的漏洞并给出修复补丁。"}
    ],
    max_tokens=32768
)
print(response.choices[0].message.content)

# 轻量版：多模态输入（图片 + 文本）
response = client.chat.completions.create(
    model="glm-5.3-flash",
    reasoning_effort="low",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "根据这张设计稿生成对应的 React 组件。"},
            {"type": "image_url", "image_url": {"url": "https://example.com/mockup.png"}}
        ]
    }],
    max_tokens=8192
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-api-key",
  baseURL: "https://api.apiyi.com/v1",
});

const response = await client.chat.completions.create({
  model: "glm-5.3-flash",
  reasoning_effort: "low",
  messages: [
    { role: "user", content: "分析这 70 万行服务器日志，找出根因。" }
  ],
  max_tokens: 16384,
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}