●OPUS48 — The default model on Bedrock, Vertex, and AWS is now Claude Opus 4.8. Opus 4.8 and Haiku 4.5 are also in the Messages API, with prompt caching and extended thinking●STREAM — A Claude Code stability and quality update landed: subagent text over stream-json, stronger permission and hook handling, and better background-agent reporting●FASTEND — Fast mode for Claude Opus 4.7 is removed on July 24. After that, speed: 'fast' returns an error, so migrate to fast mode on Opus 4.8●TEACH — Claude for Teachers is here, giving verified US K-12 educators free premium access, plus curriculum connections aligned to standards in all 50 states and new education connectors●FIX — The update fixes issues across Chrome, Windows, Bedrock, Vertex, hooks, and session recovery, and speeds up terminal rendering●IPO — Bankers are reportedly lining up investor meetings for Anthropic ahead of a possible public listing as soon as October●OPUS48 — The default model on Bedrock, Vertex, and AWS is now Claude Opus 4.8. Opus 4.8 and Haiku 4.5 are also in the Messages API, with prompt caching and extended thinking●STREAM — A Claude Code stability and quality update landed: subagent text over stream-json, stronger permission and hook handling, and better background-agent reporting●FASTEND — Fast mode for Claude Opus 4.7 is removed on July 24. After that, speed: 'fast' returns an error, so migrate to fast mode on Opus 4.8●TEACH — Claude for Teachers is here, giving verified US K-12 educators free premium access, plus curriculum connections aligned to standards in all 50 states and new education connectors●FIX — The update fixes issues across Chrome, Windows, Bedrock, Vertex, hooks, and session recovery, and speeds up terminal rendering●IPO — Bankers are reportedly lining up investor meetings for Anthropic ahead of a possible public listing as soon as October

TAG

latency

2 articles

← Back to all tags

claude-api² production² performance¹ infrastructure¹ tool-use¹ parallel¹

⬡ API & SDK/2026-04-28Intermediate

Four Infrastructure Levers That Cut Claude API Latency Before You Touch the Model

Before you downgrade Sonnet to Haiku to chase faster responses, the network and request shape around your Claude API calls usually has more headroom. Here are four infrastructure levers — region selection, connection pooling, prompt caching, and streaming — with code and measurement notes.

⬡ API & SDK/2026-04-23Advanced

Running Claude API Parallel Tool Use in Production — Controlling Concurrency, Designing for Partial Failure, and Cutting Latency

Claude API's parallel tool use can cut agent latency in half — but partial failures and state conflicts show up fast in production. Here's how to control concurrency, design error handling, and add observability.