◉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 /config●CACHE — 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 changed●CONFIG — 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_MODEL●NOTIFY — 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 polling●SECURITY — 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 file●PRICING — 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●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 /config●CACHE — 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 changed●CONFIG — 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_MODEL●NOTIFY — 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 polling●SECURITY — 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 file●PRICING — 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

Rate limit

2 articles
← Back to all tags
Related:
Claude API24292Headers1Throttling1Cost attribution1Production1retry1production1
⬡ 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/2026-03-29Intermediate

Claude API 429 Errors in Production: Lessons from Six Parallel Content Pipelines

When Claude API starts returning 429 Too Many Requests, the official exponential-backoff snippet alone is rarely enough. Drawing on six content pipelines run by one indie developer, this guide covers the real failure modes I have observed, working Python and TypeScript retry implementations with jitter, a token-bucket throttle, and concrete criteria for moving jobs to the Batch API.