Problems / LLM serving, hard

An AI assistant at 200 chats a second: cost and an outage

Asked at OpenAI, Anthropic and AI product companies. Every chat sends a 6,000-token prompt (system prompt, tools and retrieved context) to a frontier model and streams back 400 tokens. At 15 s provider A has a 12-second outage. The token bill alone is several times the budget.

Solve it in the labTake it as a mock interview

Unlock it once for 25 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 99% and time to first token p99 ≤ 3 s through the outage, for at most $4,000,000 a month.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 5; 2 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. Peak hour. 25% more traffic than the problem states, with the same failures.
  3. A slow dependency. The main data store or model answers twice as slowly for part of the run.

The traffic

200 requests a second for 40 seconds: 100% chat (reads).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls AI gateway.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
AI gatewayApp serviceLoad balancer forwards to it.Calls Frontier model (provider A).Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.4 replicas × 2000 slots · timeout 20 s
Frontier model (provider A)LLM endpointAI gateway calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second.4000 streams · 60,000 calls/min

More llm serving problems