claude-sonnet-4-5 stops on November 30 — I checked the bill before calling its replacement cheaper
claude-sonnet-4-5-20250929 retires on November 30, 2026. The recommended claude-sonnet-5-5 has lower list prices, but a new tokenizer and a 400 on temperature change the math. After reading, you can audit your own calls and plan the switch in order.
The Week Opus 5.5 Became the Default, I Counted the Places I'd Left as Aliases
Claude Code 2.1.280 made Opus 5.5 the default Opus and moved Pro's default from Sonnet to Opus. Before touching a single setting, I checked three things: what the alias resolves to, whether a saved /effort carries over, and what $0.20 cache reads do to a monthly estimate. Scripts included.
Character counts won't predict PDF input tokens — bracket the cost per page before you send
How to estimate the input tokens of a PDF before sending it to the Claude API, by bracketing from page count rather than character count. Includes a measured 6.6x gap on a nine-page A4 document, the two separate increases that come with current models, and the count_tokens limitation that bites when you use file_id.
Writing 25 as your session budget caps it at twenty-five cents
Managed Agents session budgets are expressed in minor units as a string. Here is how I mixed up the unit, hit budget_reached in minutes, and what raising versus clearing a budget actually does.
The 200K-Token Cliff That Doubled My Nightly Bill — A count_tokens Preflight to Avoid Long-Context Pricing
Sonnet 5's native 1M context switches the entire request to long-context pricing the moment input crosses 200K tokens. Here's how I caught that silent cost cliff before sending, using the billing-exempt count_tokens API, with working Python and TypeScript code.
We Collected Plenty of Claude Code Usage Data — Then Budgeting Still Didn't Work. Field Notes on Cost Attribution and Idle Seats
The Claude Code Analytics API gives you data, but data alone doesn't run a budget. Here are field notes on turning raw usage logs into cost attribution, idle-seat detection, and alerts that don't cry wolf — with working code and the thresholds we actually use.