Quiz · 5 questions
👁️ Vision & Multimodal
Images in, images out, audio, PDFs
Level 0Tokenizer
0 XP0/54 lessons0/10 achievements
0/120 XP to next level120 XP to go0% complete
Quiz
01URL vs base64 image input — what's the cost difference?
Hint
It's the bytes of the image, not the protocol.
02detail='low' costs how many image tokens?
Hint
It's a constant.
03For OCR over a dense document scan, which detail level is right?
Hint
Fine details = more patches.
04For new image-generation work, which model should you reach for?
Hint
It's the newest first-party.
05PDF in, structured records out. Which two pieces wire this together?
Hint
One way in, one way out.
Comments 0
🔔 Reply notifications (sign in)Sign in — Please sign in to comment.
No comments yet — be the first.