文本生成（Text Generation）

export API_KEY="YOUR_API_KEY"

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["API_KEY"],
    base_url="https://api.siflow.cn/model-api",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.6-27B",
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant. Keep answers concise.",
        },
        {
            "role": "user",
            "content": "What are the main benefits of microservices architecture?",
        },
    ],
    temperature=0.7,
    max_completion_tokens=1024,
)

print(response.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["API_KEY"],
    base_url="https://api.siflow.cn/model-api",
)

response = client.chat.completions.create(
    model="qwen/qwen3.8-max",
    messages=[
        {
            "role": "system",
            "content": "You are a data analysis expert. Output results in Markdown with clear sections and bullet points.",
        },
        {
            "role": "user",
            "content": "Summarize typical patterns in SaaS trial-to-paid conversion by cohort (e.g. by signup week). What metrics and recommendations would you highlight? Keep it under 300 words.",
        },
    ],
    temperature=0.5,
    max_completion_tokens=1024,
)

print(response.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["API_KEY"],
    base_url="https://api.siflow.cn/model-api",
)

response = client.chat.completions.create(
    model="glm-5.2",
    messages=[
        {
            "role": "system",
            "content": "You write concise release notes. Use a short intro and bullet points.",
        },
        {
            "role": "user",
            "content": "Draft release notes for v2.0 of a CLI tool. New in this version: added `config` and `run` subcommands, support for env-based config, and a `--dry-run` flag. Keep it under 150 words.",
        },
    ],
    temperature=0.5,
    max_completion_tokens=512,
)

print(response.choices[0].message.content)