CLAUDE LABJP
OUTPUT — v2.1.237 ships a built-in Concise output style that leads with results and skips preamble, without cutting any corners on the work itself. Pick it under Output style in /configCACHE — v2.1.237 fixes prompt caching for sessions running through an LLM gateway or a custom base URL. If you work behind a company proxy, your effective per-token cost just changedCONFIG — v2.1.236 adds ANTHROPIC_DEFAULT_MODEL to set which model new sessions start on. A /model pick still overrides it and persists across restarts, unlike ANTHROPIC_MODELNOTIFY — With notify_when_idle in v2.1.236, one Claude Code session can ask another on the same machine for a single heads-up when it next goes idle. Opt-in, one-shot, no pollingSECURITY — On macOS, wildcard read-deny rules now win inside allowed read regions, cover the contents of matched directories, and can no longer be sidestepped by renaming the filePRICING — Claude Sonnet 5's introductory $2 per million input and $10 output ends August 31, with standard $3 and $15 pricing starting September 1. Ten days to goOUTPUT — v2.1.237 ships a built-in Concise output style that leads with results and skips preamble, without cutting any corners on the work itself. Pick it under Output style in /configCACHE — v2.1.237 fixes prompt caching for sessions running through an LLM gateway or a custom base URL. If you work behind a company proxy, your effective per-token cost just changedCONFIG — v2.1.236 adds ANTHROPIC_DEFAULT_MODEL to set which model new sessions start on. A /model pick still overrides it and persists across restarts, unlike ANTHROPIC_MODELNOTIFY — With notify_when_idle in v2.1.236, one Claude Code session can ask another on the same machine for a single heads-up when it next goes idle. Opt-in, one-shot, no pollingSECURITY — On macOS, wildcard read-deny rules now win inside allowed read regions, cover the contents of matched directories, and can no longer be sidestepped by renaming the filePRICING — Claude Sonnet 5's introductory $2 per million input and $10 output ends August 31, with standard $3 and $15 pricing starting September 1. Ten days to go
TAG

Cost attribution

2 articles
Back to all tags
Related:
Claude API2Rate limit14291Headers1Throttling1Production1multi-tenant1SaaS1rate limiting1Row Level Security1TypeScript1production1
API & SDK/2026-07-07Advanced

When Claude API Suddenly Starts Returning 429 in Production — Field Notes on Measuring Rate-Limit Headroom from Headers and Throttling Before You Run Dry

Scrambling to add retries after a 429 is always a step behind. Claude API writes how much you have left into every response header. These are field notes on measuring that headroom continuously and throttling yourself before it runs out.

API & SDK/2026-06-17Advanced

Making the Numbers Add Up in a Multi-Tenant Claude API SaaS — Field Notes on Isolation and Cost Attribution

The first thing that breaks when you make a Claude API SaaS multi-tenant is the month-end reconciliation. Here are field notes on a single metering chokepoint, atomic counters, reconciling against Anthropic's bill, and proving tenant isolation with adversarial tests — with production TypeScript.