CLAUDE LABJP
DEFAULT — Claude Sonnet 5 is now the default model for Free and Pro users worldwide. It's the most agentic Sonnet yet and performs close to Opus 4.8 on many tasksPRICE — Sonnet 5 launch pricing ($2 in / $10 out per million tokens) runs through August 31, then returns to $3 / $15. Worth measuring your real token costs nowFASTEND — Fast mode for Claude Opus 4.7 is removed on July 24 — three days left. If you set speed: 'fast', move those calls to fast mode on Opus 4.8MEMORY — Claude's memory now works as a set of individual, categorized entries that Claude reads and updates mid-conversation, so it's easier to see what's storedHIPAA — Enterprise and API organizations can now configure HIPAA support themselves: BAA review, guide download, and one-step enablementADMIN — The Admin API can list members, change roles, remove people, and manage groups — helpful for organizations with frequent membership changesDEFAULT — Claude Sonnet 5 is now the default model for Free and Pro users worldwide. It's the most agentic Sonnet yet and performs close to Opus 4.8 on many tasksPRICE — Sonnet 5 launch pricing ($2 in / $10 out per million tokens) runs through August 31, then returns to $3 / $15. Worth measuring your real token costs nowFASTEND — Fast mode for Claude Opus 4.7 is removed on July 24 — three days left. If you set speed: 'fast', move those calls to fast mode on Opus 4.8MEMORY — Claude's memory now works as a set of individual, categorized entries that Claude reads and updates mid-conversation, so it's easier to see what's storedHIPAA — Enterprise and API organizations can now configure HIPAA support themselves: BAA review, guide download, and one-step enablementADMIN — The Admin API can list members, change roles, remove people, and manage groups — helpful for organizations with frequent membership changes
ARTICLES

All Articles

All (786) Claude AI (133) Claude Code (320) Cowork (54) API & SDK (279)
API & SDK/2026-06-22Advanced

When Your Claude API Cost Math Doesn't Match the Bill: Accounting for the Four Token Buckets

Turn on prompt caching and your homegrown cost tally drifts from the console bill. Here is how to weight the four token buckets the usage object returns and build a ledger you can reconcile.

API & SDK/2026-06-22Advanced

Claude API Streaming Breaks the "Everything Arrives" Assumption — Field Notes on Recovering from Partial Failure

Once concurrency climbs, Claude API streams disconnect mid-response, replay events, and emit half-finished tool arguments. Treating partial failure as the norm rather than an anomaly, here is how I rebuilt the implementation and monitoring to recover quietly.

API & SDK/2026-06-22Advanced

Putting a Ceiling on the pause_turn Loop: Running Long Server Tools Safely Unattended

A production design for continuing pause_turn safely in unattended runs, where long server tools like web_search and code execution are involved. Covers branching all four stop_reason values in one loop, capping continuations and wall-clock time, and accumulating usage across paused segments.

API & SDK/2026-06-21Advanced

Surviving the 90-Second Code Execution Cell Limit with Checkpointed Chunking

Claude's code execution tool now enforces a 90-second per-cell limit. Here is how to keep a long batch from getting cut off there: persist progress to the container filesystem and resume across cells, with working code for timing, idempotent checkpoints, and knowing when to offload.

API & SDK/2026-06-21Advanced

Connecting Managed Agents to Services You Don't Want to Expose: MCP Tunnel Design

How to connect Claude Managed Agents to an internal MCP server that is never exposed to the public internet. We cover the MCP tunnel, self-hosted sandboxes, authorization boundaries, and graceful degradation when things break.

API & SDK/2026-06-21Advanced

Don't Carry Search Results Twice: Trimming Consumed Blocks with response_inclusion

When an agent runs dynamic filtering, output tokens balloon because the raw search-result blocks a code execution call already consumed get echoed back into the response. Here is when response_inclusion: excluded is safe to use, when you must keep full, with implementation and a decision table.

API & SDK/2026-06-21Advanced

Reserving Priority Capacity for User Traffic with service_tier

If you pay for Priority Tier but your user-facing responses still slow down at peak, the culprit is often your own background jobs eating the priority pool. Here is how to read service_tier, prove the contention, and isolate background work.

API & SDK/2026-06-20Advanced

Routing the effort Parameter Per Stage to Balance Claude's Output Cost and Latency

Claude's effort parameter governs all output tokens — thinking, prose, and tool calls. This guide replaces a blanket high setting with per-stage tiers and a dynamic router, grounded in measurements from a solo developer's automation pipeline.

API & SDK/2026-06-20Advanced

Running Subagents in Parallel Without One Failure Sinking the Whole Run

A fan-out / fan-in design for running several subagents in parallel, covering token budgeting, a result contract, and partial-failure handling. Includes an implementation where one branch can fail without stopping the rest, plus measured numbers.

API & SDK/2026-06-20Advanced

Putting Cloudflare AI Gateway in Front of Claude Made the Numbers I Needed Disappear — Field Notes on Instrumentation

After putting Cloudflare AI Gateway in front of Claude API, here is where I actually got stung — cost attribution, semantic-cache false hits, fallback quietly lowering quality, and budgets that don't really stop anything — with the code I used to fix each.

API & SDK/2026-06-19Advanced

Grounding Claude on Your Own Knowledge Base with search_result Blocks

How to stop your own RAG setup from losing track of which article it cited, using Claude's search_result content block and structured citations — with real numbers from running it across four sites.

API & SDK/2026-06-19Advanced

When Your Claude × Playwright Browser Agent Fails While Reporting Success — Verifying Actions and Catching UI Drift

A vision-driven Claude + Playwright browser agent fails quietly: it reports success while nothing actually changed. Here is how to stop trusting self-reports, verify each action against the goal, and detect UI drift before it breaks you.