動画理解 API

from openai import OpenAI
import base64

client = OpenAI(
    api_key="YOUR_API_KEY",            # Replace with your APIYI key
    base_url="https://api.apiyi.com/v1"
)

{/* Read the local video and base64-encode it (entire request ≤ 20 MB) */}
with open("demo.mp4", "rb") as f:
    video_b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="gemini-3.5-flash",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe the content of this video in detail"},
            {
                "type": "image_url",
                "image_url": {"url": f"data:video/mp4;base64,{video_b64}"},
                "mime_type": "video/mp4",
            },
        ],
    }],
)

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

curl https://api.apiyi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Summarize this video"},
        {"type": "image_url",
         "image_url": {"url": "data:video/mp4;base64,<BASE64_VIDEO>"},
         "mime_type": "video/mp4"}
      ]
    }]
  }'

from google import genai
from google.genai import types

client = genai.Client(
    api_key="YOUR_API_KEY",
    http_options={"base_url": "https://api.apiyi.com"}
)

response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents=types.Content(parts=[
        types.Part(file_data=types.FileData(
            file_uri="https://www.youtube.com/watch?v=VIDEO_ID"
        )),
        types.Part(text="Summarize the main content and key points of this video"),
    ]),
)

print(response.text)

Describe what happens between 00:30 and 01:15, and identify the on-screen text that appears at 02:40.