You are adding image support to your assistant. What happens to your p99 latency and your bill?

Everyone budgets image tokens. Almost nobody budgets image latency. Images are a prefill problem, prompt caching stops paying for itself, and the cheapest answer is often not to call a VLM at all.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.

Everyone budgets image tokens. Almost nobody budgets image latency. Images are a prefill problem, prompt caching stops paying for itself, and the cheapest answer is often not to call a VLM at all.

Unlock the other 754 answers · ₹2,000 / $25includes both full courses · progress stays saved · 6 months · one payment · no auto-renew

LEARN THE BACKGROUND

These lessons teach the material this question tests, in order and from the beginning.

Applied AI Engineering·ProductionSign in13mLatency, cost and quality: pick your constraintThree quantities you cannot maximise at once, and the levers that move each. Most systems are tuned by accident; this lesson is how to decide deliberately, starting from the requirement rather than from the model.

UP NEXT ON YOUR JOURNEY

Next in this trackHow do you evaluate a multimodal document-QA system, and tell a perception failure from a reasoning one?Next in this trackYour AI feature works in English and falls apart in other languages. How do you actually ship multilingual support?Popular right nowWhy do transformers scale attention scores by 1/√d_k, and what breaks if you skip it?

DISCUSSION · 0

No comments yet — be the first to share your approach.