Why this many tokens, OCR with gpt-4o-mini?

response = self.openai_client.chat.completions.create(

            model=self.settings.OCR_MODEL_ID,

messages=[

{“role”: “system”, “content”: “Get ONLY MARKDOWN from that image.”},

{“role”: “user”, “content”: [{

“type”: “image_url”,

“image_url”: {

“url”: f"data:image/jpeg;base64,{image_base64}",

“detail”: “high”

}

}]

}

],

max_tokens=self.settings.MAX_TOKENS

)

output tokens: (completion_tokens=82, prompt_tokens=25520, total_tokens=25602)
image size: Size of the buffer: 36490 Bytes
image size: 768x618
the model is “gpt-4o-mini“

Search is your friend.

Existing topics cover this already, e.g.:

2 Likes