Stage 1 · Lesson 4 of 8
Token pricing and rate limits
Hosted models charge per million tokens. Input (what you send) and output (what the model writes) have separate prices, and output usually costs several times more. Here is how works out in practice.
Take a request with 3,000 input tokens and 500 output tokens, on a model priced at $3 and $15 per million. Input costs about $0.009 and output about $0.0075, so roughly 1.7 cents per request. At 100,000 requests a month, that is about $1,650.
Providers also set : caps on requests per minute and tokens per minute for your account. Go over them and you get 429, an error that means "too many requests". Do this arithmetic before you build. A feature that works in a demo can be too expensive or too rate limited to launch.
A question to check yourself, an AI practice session and 2 cheat sheet entries come with the full roadmap. Unlock
Resources for this stage
Start with· follow one of these
- CoursePaidGrokking Modern AI Fundamentals
Design Gurus · Beginner · $72 one-time
Structured grounding in models, transformers and embeddings before you build on them
- VideoFreeDeep Dive into Large Language Models like ChatGPT
Andrej Karpathy · Intermediate
Free: Karpathy on tokens, training and why models hallucinate, in one sitting
Keep handy
Also worth your time
Input vs output tokens and a step by step cost estimate you can reuse for any feature
- Neural Networks: Zero to HeroGo deeper
Build a small GPT from scratch if you want to see the machinery for yourself