◉CLAUDE LABJP
●CC 2.1.327 — Claude Code 2.1.327 (11/18) adds claude mcp add-json, which reads a server's JSON from stdin●MCP.JSON — The same release stops project-scope mcp add and remove from wiping other keys in .mcp.json●SONNET 4.5 — Retires on the Claude API on 11/30, 11 days left. Sweep model IDs in code and saved settings in one pass●GATEWAY — Users report that behind a gateway, 1M-context models compact so late that each reply takes tens of seconds●NEON — Gemini 4 Neon went GA on 11/18. If you run it next to Claude Code, keep each tool's MCP config separate●NEW — Linked Billing 402 or 403? Find Whose Wallet Is Empty First●CC 2.1.327 — Claude Code 2.1.327 (11/18) adds claude mcp add-json, which reads a server's JSON from stdin●MCP.JSON — The same release stops project-scope mcp add and remove from wiping other keys in .mcp.json●SONNET 4.5 — Retires on the Claude API on 11/30, 11 days left. Sweep model IDs in code and saved settings in one pass●GATEWAY — Users report that behind a gateway, 1M-context models compact so late that each reply takes tens of seconds●NEON — Gemini 4 Neon went GA on 11/18. If you run it next to Claude Code, keep each tool's MCP config separate●NEW — Linked Billing 402 or 403? Find Whose Wallet Is Empty First
Articles/API & SDK
⬡ API & SDK/2026-07-05Advanced

Fable 5 Is Back Worldwide and Sonnet 5 Is the Default — Where Each of the Three Models Belongs in a Solo Automation Stack

With Fable 5 redeployed worldwide and Sonnet 5 now the default, solo automation suddenly has three capable top-tier models to reach for. Instead of ranking them, this piece assigns each a role and captures that in a policy object with a fallback ladder and run-level logging.

Claude API148model selection4automation110Fable 53Sonnet 58Opus 4.84

✦ Premium Article

On the morning of June 30th I opened the logs for a scheduled job that should have been identical to the night before, and paused. The output had shifted, just slightly. The cause was quick to find: Claude Sonnet 5 had become the default across all plans, and any job that hadn't pinned a model had quietly moved to the new default overnight.

A few days earlier, on July 1st, Fable 5 had returned to worldwide availability after export restrictions were lifted. That left me with three top-tier models reachable from my own automation at once: Sonnet 5, Fable 5, and Opus 4.8. More options is a good problem to have, but the moment you start choosing among them by asking "which one is smartest," you usually hit a wall. As an indie developer running unattended article generation and monitoring across several sites, I spent those days rethinking not "which one do I use" but "where do I put each one." Here is that placement, and how I pushed it down into code.

Why not leave it to the default model

What that opening moment really exposes is the fragility of running without a pinned model. The default changes for reasons on the platform's side. The June 30th switch was a benign, announced change — and even so, "the character of the output differs between yesterday and today" is not a small tremor for anyone running things unattended.

Leaving it to the default means tying your automation's behavior to someone else's decision. Cost, latency, output granularity — all of them ride along when the default moves. So the first principle is simple: in production automation, always pin the model explicitly. Then decide, with intent and per task, which model to pin. That is where the real work begins.

See the three models by role, not by rank

Line the three up and try to rank them, and you end up comparing benchmark numbers while losing the connection to your own tasks. Instead, I keep a one-line sense of where each one earns its place.

ModelWhere it earns its placeModel string
Sonnet 5The everyday workhorse for planning, tool use, and autonomous execution. Cheap enough at the introductory price to run constantlyclaude-sonnet-5
Fable 5Single-pass generation of long deliverables and large-context passes, leaning on always-on adaptive thinking and 128k-token outputclaude-fable-5
Opus 4.8Central judgment calls that need multi-step reasoning and consistency across long-running workclaude-opus-4-8

These three rows are a division of labor, not a ranking. Sonnet 5, as the most agentic Sonnet yet, sits as the default for everyday work that calls tools and advances through steps. I reach for Fable 5 only where 128k output and always-on thinking pay off — drafting a full article in one pass, sweeping a large log in a single go. Opus 4.8 I reserve for the central calls where a mistake throws off everything downstream, choosing spots that justify the cost. My hands-on notes from running two of them side by side are in three days with Fable 5 and Opus 4.8 side by side, but the takeaway was the same: it's about role, not who wins.

✦

Thank you for reading this far.

Continue Reading

What follows includes implementation code, benchmarks, and practical content we hope you'll find useful. This site runs without ads — server and development costs are supported entirely by members like you. If it's been helpful, we'd be truly grateful for your support.

WHAT YOU'LL LEARN
✦A way to sort tasks by role rather than rank, mapping Fable 5 / Sonnet 5 / Opus 4.8 to layers by what each does best (128k single-pass output, the everyday agentic workhorse, long-run reasoning consistency)
✦A Python policy object that looks up the model by task class instead of hardcoding model strings, with a per-class fallback ladder for when a model is unavailable
✦A logging step that records the resolved model per run, so you can verify what ran on which model even on a day the platform default changes
Secure payment via Stripe · Cancel anytime
✦

Unlock This Article

Get full access to the rest of this article. Buy once, read anytime. This site is ad-free — your support goes directly toward keeping it running.

or
Unlock all articles with Membership →
Share

Thank You for Reading

Claude Lab is ad-free, supported entirely by members like you. We publish practical guides daily with implementation code, benchmarks, and production-ready patterns. If you've found it useful, we'd love to have you on board.

  • ✦Copy-paste ready implementation code
  • ✦New advanced guides published daily
  • ✦$5/mo or $10 for lifetime access
View Membership →

Related Articles

⬡ API & SDK2026-08-23
The September Price Increase for Sonnet 5 Isn't Happening. Rebuilding a Forecast I Got Wrong in July
Sonnet 5's introductory $2/$10 pricing was supposed to rise to $3/$15 on September 1. It won't. Here's how to recompute your own effective cost from the usage numbers you already have, with working code.
⬡ API & SDK2026-05-15
Automating Wallpaper Classification with Claude Vision API — Accuracy, Cost, and a Batch Job That Survives Interruptions
A firsthand account of automating wallpaper category classification with the Claude Vision API. Honest numbers on accuracy and cost, plus the batch design that stopped me re-paying for the same images.
⬡ API & SDK2026-11-18
Before Your Customers Pay Through Linked Billing: Reading a 402 or 403 to Find Whose Wallet Is Empty
Linked billing, released in beta on November 17, lets you choose who pays on every Claude API request through billing_policy. When a request billed to a customer comes back as a 402 or 403, here is how I work out which wallet is the cause, when to pay for it myself, and a small Python wrapper that keeps that decision in one place.