Python SDK

HiAPI 完全兼容 OpenAI Python SDK。只需更改 base_url 即可。

安装

pip install openai

配置

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.hiapi.ai/v1"
)

或使用环境变量：

export OPENAI_API_KEY="YOUR_API_KEY"
export OPENAI_BASE_URL="https://api.hiapi.ai/v1"

from openai import OpenAI
client = OpenAI()  # reads from env

图像生成

response = client.images.generate(
    model="qwen-image-2.0",
    prompt="一张春季活动海报，包含中文标题",
    size="2048x2048"
)

image_url = response.data[0].url
print(image_url)

聊天补全（对话式生图）

import requests

response = requests.post(
    "https://api.hiapi.ai/v1/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "Nano-Banana",
        "stream": False,
        "messages": [{"role": "user", "content": "draw a cute cat"}],
        "extra_body": {
            "google": {
                "image_config": {"aspect_ratio": "1:1", "image_size": "1K"}
            }
        }
    }
)

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

视频端点（requests）

对于当前视频端点，请使用 requests：

import requests

response = requests.post(
    "https://api.hiapi.ai/v1/videos",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "wan2.7-t2v",
        "prompt": "sunset timelapse over mountains",
        "seconds": "5"
    }
)

print(response.json())