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"
)

with open("demo.mp4", "rb") as f:
    video_b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="seed-2-0-pro-260328",       # or qwen3.8-flash / kimi-k3 / gemini-3.8-flash, etc.
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this video in detail and give timestamps for the key moments"},
            {
                "type": "video_url",
                "video_url": {"url": f"data:video/mp4;base64,{video_b64}"},
                # or pass a public URL directly (not on Gemini): {"url": "https://your-bucket.example.com/demo.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": "seed-2-0-pro-260328",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Summarize this video"},
        {"type": "video_url",
         "video_url": {"url": "data:video/mp4;base64,<BASE64_VIDEO>"}}
      ]
    }]
  }'

response = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this video in detail"},
            {
                "type": "image_url",
                "image_url": {"url": f"data:video/mp4;base64,{video_b64}"},
                "mime_type": "video/mp4",
            },
        ],
    }],
)

from google import genai
from google.genai import types

client = genai.Client(
    api_key="YOUR_API_KEY",            # Replace with your APIYI key
    http_options={"base_url": "https://api.apiyi.com"}
)

with open("demo.mp4", "rb") as f:
    video_bytes = f.read()

response = client.models.generate_content(
    model="gemini-3.8-flash",
    contents=types.Content(parts=[
        types.Part.from_bytes(data=video_bytes, mime_type="video/mp4"),
        types.Part(text="Describe this video in detail and mark the timestamps of key moments"),
    ]),
)

print(response.text)
print(response.usage_metadata.prompt_tokens_details)  # includes a VIDEO entry when the video reached the model

# Build the request body (macOS / Linux)
printf '{"contents":[{"parts":[{"inline_data":{"mime_type":"video/mp4","data":"%s"}},{"text":"Summarize this video"}]}]}' \
  "$(base64 < demo.mp4 | tr -d '\n')" > req.json

curl "https://api.apiyi.com/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d @req.json

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-3.8-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 information in this video"),
    ]),
)

print(response.text)

import base64, subprocess, glob

# Extract one frame every 2 seconds (requires ffmpeg installed locally)
subprocess.run(["ffmpeg", "-i", "demo.mp4", "-vf", "fps=0.5", "frame-%02d.jpg"], check=True)

frames = []
for path in sorted(glob.glob("frame-*.jpg")):
    b64 = base64.b64encode(open(path, "rb").read()).decode()
    frames.append({"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{b64}"}})

response = client.chat.completions.create(
    model="gpt-6-sol",
    messages=[{
        "role": "user",
        "content": [{"type": "text", "text": "These are frames taken every 2 seconds from one video, in time order. Describe the video."}] + frames,
    }],
)

Describe what happens between 00:30 and 01:15, and tell me what text appears at 02:40.