Call a hosted model and read the bill

Put your key and a model name in the environment

Keep the key in your shell or a .env file that git ignores. Never paste it into a script.

Run this to check

You pass when

It prints ready. MODEL holds a model id you picked from the OpenRouter model list (filter by price: free).

Write chat.py: one system message, one user message, print the answer and the usage

Use the openai package with base_url set to https://openrouter.ai/api/v1. The same script talks to Ollama if you point base_url at http://localhost:11434/v1.

Run this to check

You pass when

An answer prints, then one line with prompt tokens and completion tokens.

Files you write

• chat.py

Add a --chat mode that resends the whole conversation each turn

The model remembers nothing. The conversation is a list you keep and send again, which is why long chats cost more per turn.

Run this to check

You pass when

Tell it your name in turn one and ask for it in turn two: it answers correctly, and the prompt token count grows every turn.

Files you write

• chat.py

Print the cost of each call from the model's listed prices

Run this to check

You pass when

A cost line prints in dollars. On a free model it is 0, so also print what the same call would cost on one paid model you name.

Files you write

• chat.py