CLAUDE LABJP
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 thinkingSTREAM — A Claude Code stability and quality update landed: subagent text over stream-json, stronger permission and hook handling, and better background-agent reportingFASTEND — 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 4.8TEACH — 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 connectorsFIX — The update fixes issues across Chrome, Windows, Bedrock, Vertex, hooks, and session recovery, and speeds up terminal renderingIPO — Bankers are reportedly lining up investor meetings for Anthropic ahead of a possible public listing as soon as OctoberOPUS48 — 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 thinkingSTREAM — A Claude Code stability and quality update landed: subagent text over stream-json, stronger permission and hook handling, and better background-agent reportingFASTEND — 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 4.8TEACH — 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 connectorsFIX — The update fixes issues across Chrome, Windows, Bedrock, Vertex, hooks, and session recovery, and speeds up terminal renderingIPO — Bankers are reportedly lining up investor meetings for Anthropic ahead of a possible public listing as soon as October
ARTICLES

All Articles

All (786) Claude AI (133) Claude Code (320) Cowork (54) API & SDK (279)
API & SDK/2026-07-19Advanced

When Prompt Caching Was On but the Bill Didn't Move — Field Notes on Instrumenting cache_read to Close the Hit-Rate Gap

You added cache_control but your Claude API bill barely changed. Before guessing at fixes, record cache_read and cache_creation on every request and split the hit-rate gap into three causes: non-deterministic prefixes, TTL expiry, and sub-threshold blocks.

API & SDK/2026-07-14Advanced

A Two-Stage Pre-Publish Gate for User-Facing AI Text in Consumer Apps

Design a two-stage pre-publish gate for short AI-generated text you ship to end users: a deterministic rule layer plus a Claude classifier, with fail-closed handling, generation-time vetting, and a cost model. Full implementation code included.

API & SDK/2026-07-13Advanced

Precision Lives in the Second Stage: Reranking a Personal Knowledge Search with Claude

Embedding search alone leaves 'semantically close but not the answer' passages at the top. This is a two-stage design that gathers candidates broadly, then lets Claude reorder them by answerability, with structured scoring, abstention, and a cost estimate.

API & SDK/2026-07-13Advanced

Coalescing Concurrent Claude API Calls: Single-Flight Against Duplicate Inference and Cache Stampede

A design for collapsing identical prompts that fire at the same instant into a single upstream Claude call, using single-flight (request coalescing). In-process and distributed implementations, jittered retries, and negative caching, with measured results.

API & SDK/2026-07-13Advanced

Full-Size or Downscaled? A Per-Image Resolution Rule for Opus 4.7's High-Resolution Vision

Opus 4.7 finally read the fine texture in my wallpapers, so I sent everything at full size. My weekly image tokens jumped 2.4x. Here is the preflight that decides resolution and model per image, with the measured savings.

API & SDK/2026-07-13Advanced

When Extended Thinking Flattened My Accuracy but Doubled the Bill — Field Notes on Measuring the Marginal Utility of Thinking Tokens

You pinned budget_tokens high 'to be safe,' accuracy barely moved, and the bill kept climbing. These field notes show how to ledger real thinking-token usage by p50/p95/hit-rate and measure how much accuracy each extra 1,000 thinking tokens actually buys.

API & SDK/2026-07-12Advanced

Designing Around Claude API 413 request too large — Preflight Sizing and Splitting

Pack too much text, images, and tool_result into one request and Claude API rejects it with 413 request too large. Here is a code-backed design for measuring request bytes before you send, telling the two kinds of 413 apart, and splitting requests without breaking them.

API & SDK/2026-07-12Intermediate

When You Give an API Key an Expiration Date, Expiry Becomes a Plan Instead of an Accident

The Console now lets you set expiration dates on API keys. Here is how to fold planned expiry into unattended operations — with overlapping dual keys and a local expiry ledger — so your nightly jobs never go dark.

API & SDK/2026-07-12Advanced

A Long Non-Streaming Response Was Billed Twice Past the 10-Minute Wall: Redesigning the SDK's Default Timeout and Retries

The Anthropic SDK's default 10-minute timeout and two automatic retries can silently re-run a long non-streaming response and bill you twice. Here is how the trap works, and how to close it with streaming, explicit timeout/max_retries, and a small local ledger — with measured before/after numbers.

API & SDK/2026-07-11Advanced

Is This New Wallpaper Too Close to One We Already Ship? Near-Duplicate Detection with a Perceptual-Hash Pre-Filter and Claude Vision

A two-stage pipeline that catches the near-duplicates a SHA256 hash misses — recolored, lightly cropped, re-encoded — by pre-filtering with a perceptual hash and adjudicating only the close pairs with Claude Vision. With measured precision calibration and cost design from running a wallpaper catalog solo.

API & SDK/2026-07-11Advanced

Tightening Tool Schemas From the Arguments You See in Production

Record the arguments Claude actually passes to your tools in production, then use that distribution to add enums and patterns back into your JSON Schema. With logging code and before/after numbers.

API & SDK/2026-07-11Advanced

When Whisper Wrote 'Thanks for Watching' Into the Silence — Measuring and Killing Japanese Transcription Hallucinations

Whisper inserts phantom boilerplate into silent or noisy segments of Japanese audio. Here is how to measure hallucinations with no_speech_prob and avg_logprob, strip silence with VAD, and have Claude validate what remains — with the implementation and the routine that pulled it back.