常见问题

"enable_thinking": false

{
  "model": "zai-org/glm-4.5",
  "messages": [
    {
      "role": "user",
      "content": "北京今天天气怎么样？"
    }
  ],
  "temperature": 0.7,
  "stream": false,
  "max_tokens": 500,
  "enable_thinking": false
}

{
  "usage": {
    "prompt_tokens": 1000,
    "completion_tokens": 200,
    "total_tokens": 1200,
    "prompt_cache_hit_tokens": 800,
    "prompt_cache_miss_tokens": 200
  }
}

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ppio.com/openai",
    api_key="<Your API Key>",
)

response = client.chat.completions.create(
    model="<your-model-id>",
    messages=[{"role": "user", "content": "你好"}],
)

# 获取本次调用的 token 用量
usage = response.usage
print(f"输入 tokens: {usage.prompt_tokens}")
print(f"输出 tokens: {usage.completion_tokens}")

import time, random

def call_with_retry(fn, max_retries=5):
    for attempt in range(max_retries):
        try:
            return fn()
        except Exception as e:
            if "429" in str(e) and attempt < max_retries - 1:
                wait = (2 ** attempt) + random.uniform(0, 1)
                time.sleep(wait)
            else:
                raise

Base URL: https://api.ppio.com/openai
API Key:  您的 PPIO API Key
模型名称: 如 deepseek/deepseek-v3.2-exp、qwen/qwen3-235b 等

import time

def poll_task(task_id, client, max_wait=600, interval=10):
    """轮询视频任务结果，最长等待 600 秒"""
    elapsed = 0
    while elapsed < max_wait:
        result = client.get_task(task_id)
        status = result.get("status")
        if status == "succeeded":
            return result
        elif status == "failed":
            raise Exception(f"任务失败: {result.get('error')}")
        time.sleep(interval)
        elapsed += interval
    raise TimeoutError(f"任务 {task_id} 超时（{max_wait}s）")