CC wasn't per-token either? Nor is Codex?
From my simple checks - and from Microsoft's own blog - per token pricing isn't going to be realistic for agentic coding either.
They don't show your usage in tokens for Claude Code and Codex subscriptions, but that is how they are doing the accounting.
Claude Code is definitely token based, its been discussed extensively on Hacker News and the related Github threads. A large context cache miss can take half your usage easily in just one request... "max" just means more reasoning tokens. I've also run out of usage during a single request in CoWork. Its definitely token based.