AIMM Member Guide

The Model Selection Playbook for Content Creators

Which Claude model to use at every stage of your writing pipeline — and when paying for the premium model actually pays you back.

Know Your Lineup

Four models, four jobs. The skill isn't knowing which model is "best" — it's knowing which stage of your work each one is built for.

Claude Fable 5

$10 / $50 per 1M tokens in/out

The flagship — a new tier above Opus. Highest intelligence ceiling available.

Use for: The judgment calls that everything else depends on — picking the angle, designing the structure, drafting your highest-stakes pieces.

Claude Opus 4.8

$5 / $25 per 1M tokens in/out

The workhorse. Clear, warm prose with few AI tics. Strong editorial judgment.

Use for: Drafting, structural editing, ideation — the default spine of every pipeline.

Claude Sonnet 4.6

$3 / $15 per 1M tokens in/out

Fast, capable, economical. Excellent with tools and long source documents.

Use for: Research, fact-checking, copy editing — the volume work.

Claude Haiku 4.5

$1 / $5 per 1M tokens in/out

Fastest and cheapest. Built for simple, mechanical tasks.

Use for: Typo and grammar passes only. Never for prose you'll publish.

The Key Insight

Price differences come from per-token rates × how many tokens the model uses. A smarter model at lower effort can cost the same as a cheaper model that overthinks. Stop asking "which model is cheapest" and start asking "what's the cheapest path to the quality bar this piece needs?"

Effort: The Second Dial

Every model also takes an effort setting — how hard it thinks before writing. More effort = deeper reasoning = more tokens = more cost.

EffortWhen to use it
lowMechanical tasks — copy edits, formatting, classification
mediumBounded tasks — line edits, headlines, research summaries
highThe default for real writing work — drafting, ideation, judgment
xhighLong-arc structure — outlines and drafts of 3,000+ word pieces

Route by Stakes, Not Word Count

The single most important decision isn't which model — it's which tier the piece belongs to. Everything else follows from that.

⭐ Flagship

Pieces where one output's quality outweighs throughput:

  • Ghostwritten work in your voice
  • Named-byline placements
  • Thought leadership that builds your authority
  • Any conversion copy — landing pages, sales letters (yes, even short ones)
Why Not Word Count?

A 1,200-word sales letter deserves the flagship treatment — every sentence is load-bearing for conversion. A 3,500-word internal explainer doesn't. Stakes decide the tier. Word count only decides how much effort to apply within the tier (3,000+ words → bump high to xhigh).

Three Things That Are Always True

1

The premium model only earns its cost on judgment and generation stages — ideation, angle selection, outlining, drafting, structural editing. It never pays back on research, copy edits, or fact-checking.

2

Recurring formats favor consistency over ceiling. Your newsletter audience notices voice drift more than marginal brilliance. A stable model + locked voice brief beats a smarter model week-over-week.

3

Voice doesn't carry itself between sessions. Every stage is a fresh context. Bring a voice brief plus 2–3 anchor paragraphs from your published work into every drafting and editing session — or the prose drifts toward generic AI voice no matter which model you pay for.

The Writing Pipeline, Stage by Stage

Eleven stages from blank page to published. Toggle between tiers to see how the model assignments shift. Click any stage for the why.

Show pipeline for:

Adapting by Content Type

The pipeline doesn't change models per platform — it changes shape. Pick a content type to see which stages to keep, which to skip, and where the piece lives or dies.

The Cheat Sheet

Everything above, compressed to what you need at the moment of choosing.

Operating Rules

1

Fable 5 appears only on flagship pieces, only on judgment/generation stages (ideation, angle selection, outlining, drafting, structural edit, headlines). Never on research, line edits, copy edits, or fact-check.

2

The routine column is a complete pipeline on its own. Opus 4.8 spine + Sonnet for mechanical work = professional-grade output. If budget tightens, routine becomes the answer for everything.

3

Validate before committing the premium. These placements are reasoned, not benchmarked. Run one real flagship piece through both tiers, judge blind, and let the result decide.

4

Conversion copy is always flagship — landing pages and sales letters get the premium treatment regardless of length. Revenue per word, not words per piece.

5

Compress stages for social, don't downgrade the model for the part that matters. A LinkedIn post skips research and outlining — but the hook deserves real model attention, because the hook is the post.

The 10-Second Decision

  1. Is this ghostwritten, bylined, authority-building, or conversion copy? → Flagship tier. Fable 5 on the judgment stages.
  2. Everything else? → Routine tier. Opus 4.8 spine.
  3. Is the task mechanical (research, fact-check, typos)? → Sonnet 4.6, whatever the tier.
  4. Is the piece 3,000+ words? → Bump effort from high to xhigh on outline and draft.
  5. Always: voice brief + 2–3 anchor paragraphs in every drafting/editing session.