# claudemaster.com

> Start agent work on Claude Opus 5 (`claude-opus-5`); move to Claude Fable 5.1 for long-horizon runs. Sonnet 5 is the balance point, Haiku 4.5 the cheap tier. Independent reading room, not affiliated with Anthropic.

Editorial rules: claims about Claude and Anthropic are sourced to primary
documentation and dated. Vendor-published benchmark numbers are labelled as
such and are not independent measurements.

## Signature

- [The Harness Desk](https://claudemaster.com/) — homepage routing board for which Claude model to run agent work on.

A routing board on the homepage (https://claudemaster.com/) answering which Claude model to
run agent work on. Prices and model IDs are Anthropic's published list
figures as of 2026-09-19; the routing calls are this site's editorial
judgement applied to their guidance. Verify figures at the primary source.

| Model | API ID | In/out per MTok | Cache read per MTok | Context | Max out |
|---|---|---|---|---|---|
| Claude Fable 5.1 | `claude-fable-5-1` | $10 / $50 | $0.25 (2.5%) | 1M | 128K |
| Claude Opus 5 | `claude-opus-5` | $5 / $25 | $0.50 (10%) | 1M | 128K |
| Claude Sonnet 5 | `claude-sonnet-5` | $2 / $10 | $0.20 (10%) | 1M | 128K |
| Claude Haiku 4.5 | `claude-haiku-4-5` | $1 / $5 | $0.10 (10%) | 200K | 64K |

- Starting a new harness → `claude-opus-5`. Start on Opus 5. Anthropic’s own routing guidance is to make it the default for most workloads, and at $5/$25 per MTok it is half Fable 5.1’s base rate for the same 1M context window and 128K output ceiling.
- Long-horizon agentic runs → `claude-fable-5-1`. Fable 5.1 is the documented reach for demanding reasoning and long-horizon agentic work. On Anthropic’s published numbers its margin over Opus 5 is widest exactly here — Terminal-Bench-Science 0.1 at 52.6% against 29.0%, AutomationBench at 31.4% against 26.9% — while CursorBench 3.2.0 has them within a few points.
- Opus 5 is missing your evals → `claude-fable-5-1`. This is the escalation Anthropic names explicitly: when evals on Opus 5 at higher effort still fall short, move to Fable 5.1.
- Large cached prefix, many turns → `claude-fable-5-1`. Fable 5.1 bills cache reads at 2.5% of base input — $0.25 per MTok — where Opus 5 bills 10%, or $0.50. It is twice the base input price and half the cache-read price, and an agent loop is mostly cache reads.
- Latency over the last few points → `claude-sonnet-5`. Sonnet 5 is the documented balance point between speed and intelligence, with the same 1M context and 128K output as the tiers above it at $2/$10 per MTok.
- High-volume mechanical turns → `claude-haiku-4-5`. Haiku 4.5 at $1/$5 is the cheap tier, and the new per-message effort beta means the mechanical turns no longer have to inherit the session’s setting even when you keep them on a larger model.
- Planner and executor split → `claude-fable-5-1`. Fable 5.1 plans well enough to justify the split, with Sonnet 5 or Haiku 4.5 executing. The handoff is where the migration cost lives.

Fable 5.1 is twice Opus 5’s base input price and half its cache-read price,
so an agent loop dominated by cache reads can be cheaper on the nominally
more expensive model. Sonnet 5 introductory pricing of $2/$10 did not rise to
$3/$15 on 2026-09-01; it is now the standard rate.

## Articles

- [Picking a Claude Model for Agent Work: Fable 5.1, Opus 5, Sonnet 5, Haiku 4.5](https://claudemaster.com/claude-model-selection-2026-09/): A September 2026 engineering reference — routing defaults, cache-read economics, and the Fable 5.1 changes that will break an existing agent harness. (published 2026-09-19)
- [From Skill to CLI to npm: Building an Excalidraw Toolchain with Claude Code](https://claudemaster.com/excalidraw-toolchain/): How a single Claude Code skill turned into two published npm packages in one session — and what it reveals about building with AI agents. (published 2026-02-07)

## Optional

- [Index](https://claudemaster.com/): The Harness Desk plus the reading room
- [Full page summaries](https://claudemaster.com/llms-full.txt)