5 posts
Thirty days of running an agent fleet from chat: 8.7 billion tokens, 70,227 calls, 2,861 sessions, a 98 percent cache hit rate. At each vendor's list price that traffic bills $7,566. Three subscriptions covered it for $599. Where the tok…
I split a day of development across two AI subscriptions: judgment on the Anthropic meter, typing on Moonshot's. Five merged PRs later, here is where the tokens went, how K3's pricing actually compares, and how I'm tuning the mix.
GitHub Actions' default minute allowance is priced for a team that types at human speed. At agent velocity the bill breaks before the engineering does. Here is how a forced workaround, a local CI mirror plus local deploys, became the bet…
Prompt caching looks like a flag you flip for a cheaper bill. It is really the reuse of a stored prompt prefix, governed by three rules, and applying it across four parts of my own system showed where it pays, where it quietly does nothi…
Four days after I said goodbye to Opus, an export-control directive pulled Fable 5 offline and the fallback became the workhorse again. What I shipped in the window, what it cost, and the model-tiering plan for when Fable comes back.