Cost Generation for "Video" Processing using GPT-4o
R
Rawinder Singh
How can we generate the cost for this system:
video = cv2.VideoCapture("data/bison.mp4")
base64Frames = []
while video.isOpened():
success, frame = video.read()
if not success:
break
_, buffer = cv2.imencode(".jpg", frame)
base64Frames.append(base64.b64encode(buffer).decode("utf-8"))
video.release()
print(len(base64Frames), "frames read.")
PROMPT_MESSAGES = [
{
"role": "user",
"content": [
"These are frames from a video that I want to upload. Generate a compelling description that I can upload along with the video.",
*map(lambda x: {"image": x, "resize": 768}, base64Frames[0::50]),
],
},
]
params = {
"model": "gpt-4o",
"messages": PROMPT_MESSAGES,
"max_tokens": 200,
}
result = client.chat.completions.create(**params)
print(result.choices[0].message.content)
JC
You can view the cost by batch uploading the images in the prompt editor (image type) and test run the prompt. And then you can see the cost estimation of each image and the whole run.