Back to Devoured - October 09, 2026
DEVOURED
ICYMI we've cut the price of Sonnet 5.5 cache reads in half

ICYMI we've cut the price of Sonnet 5.5 cache reads in half

AI llm ClaudeDevs
Anthropic slashed cache read prices for Claude 3.5 Sonnet to $0.10 per million tokens, effectively reducing agentic workload costs by roughly 20%.
What: Anthropic updated the pricing for its Claude platform, specifically targeting cache reads. The change applies to API users, while existing Claude Code usage limits remain unchanged.
Why it matters: Reducing the cost of context caching is a strategic move to encourage developers to build more complex, stateful agents that require frequent access to large codebases or documents.
Decoder
  • Cache reads: The cost associated with accessing previously processed, stored information in an LLM context, which significantly lowers latency and price compared to re-processing the same input.
Original article

ClaudeDevs

ICYMI we've cut the price of Sonnet 5.5 cache reads in half.

In the Claude Platform, it's now $0.10 per million tokens (input is $2, output is $10).

This means Sonnet 5.5 now runs ~20% cheaper on most agentic work.

(API only, no change to Claude Code usage limits.)

More from @ClaudeDevs

ClaudeDevs

You can now mod Claude Code:

  • Change how it behaves
  • Customize the UI
  • Swap in your own features

Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app.

A few examples:

Token Weather adds a forecast of your context window: how full it is, plus a sparkline of your last 12 turns.

Blast Radius catches risky shell commands like rm -rf, git reset --hard, or a force push before they run. It shows what the command would touch in a side pane.

ClaudeDevs

Opus 5.5 performs at the level of Fable 5.1. It's ~30% faster and ~40% cheaper than Opus 5 per task.

In Claude Code:

  • 5-hour session limits increase 20% today
  • Opus 5.5 is priced lower, so it goes 25% further within limits
  • Pro, Max, and Team users get a reset to use anytime
https://twitter.com/claudeai/status/2102435511222890900

If you're on Pro, Max, or Team, your reset is available today in Settings → Usage. Apply it any time until Oct 22.

Opus 5.5 is the default for paid plans. It's priced lower than Opus 5, so your 5-hour and weekly limits go 25% further. Opus 5.5 is a lot better at writing too. It’s clearer, uses less jargon, and follows the writing rules you give it. Long Claude Code sessions are much easier to follow!

ClaudeDevs

We're open-soucing Claude Commerce Agents.

This is a blueprint for building shopping and merchant agents, with reference implementations across retail, travel, telecom, and entertainment.

Retailers running shopping agents on Claude have seen carts up to 35% larger and shoppers 60% more likely to complete a purchase.

See our blog to learn more about the architecture, latency & cost techniques, and eval practices: https://claude.com/blog/the-anatomy-of-effective-commerce-agents

Also, see our open-source reference implementation.

This includes shopping & merchant agents, four vertical demos, and a Claude Code plugin that builds an agent against your backend.

See here: https://github.com/anthropics/commerce-agents

ClaudeDevs

Last month you told us Remote Control was the thing you'd most like us to fix, so we've been working hard on reliability.

Here's what's better today:

You can now start a Claude Code session directly from your phone.

Any machine running claude remote-control shows up as a device card at the top of the Code tab. Tap it, pick a directory, and it starts on that machine.

Your phone now stays in sync with what's running on your machine.

Resuming a session on your laptop keeps the phone on the live session instead of archiving it. When Claude Code exits, your phone shows it offline within seconds instead of leaving a stale session hanging around

ClaudeDevs

We shipped four updates to Claude Managed Agents this week.

First, you can now set a budget for sessions to keep spend predictable. Sessions that hit the limit pause with a budget_reached event, you can raise the budget to resume.

Next, you can now control where inference runs for Claude Managed Agents.

Set model.inference_geo to US or global. Pinning to global runs wherever there's capacity at the standard rate and us keeps it in-region and bills at 1.1x.

Managed Agents now load skills from your attached repositories.

If you already keep skills in .claude/skills/ for Claude Code, Managed Agent sessions pick them up automatically at start.

ClaudeDevs

MCP 2026-07-28 is live and it's the largest update to the protocol since launch.

MCP is now stateless, making it easier to deploy and scale remote servers.

https://claude.com/blog/bringing-mcp-2026-07-28-to-claude

Before, running a remote MCP server meant managing session state, which limited where you could run it.

Now that MCP is stateless, you can deploy on serverless and edge infrastructure, or scale horizontally behind any load balancer.

Extensions are also first-class — a formal path to extend the protocol. Examples:

  1. MCP Apps: server-rendered UIs in a sandboxed iframe
  2. Tasks: long-running and async operations
  3. Enterprise Managed Auth: control MCP server access centrally via your identity provider
Explore all 55 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi