The Model Sequence — a Claude field guide

CLICK OR TAB TO A STAR — THE CARD, CONSOLE & SNIPPET BELOW FOLLOW YOUR SELECTION

01 · Object of interest Spectral card Pricing & specs from the Claude Platform docs

02 · Spectrograph Feed in a task, read out a model Answer all three; the verdict updates live

Q1 — How hard is the task, honestly?

Q2 — What are you optimizing?

Q3 — Any scale factors?

03 · Throttle The effort parameter One dial, five stops — it shapes every token, thinking and tool calls included

high

Typical use

Token spend

Tool behavior

Available on

response = client.messages.create(
    model="claude-opus-5",
    max_tokens=4096,
    messages=[{"role": "user", "content": prompt}],
    output_config={"effort": "high"},  # the whole trick
)

Gotchas worth memorizing

"high" is the default — setting it explicitly behaves exactly like omitting the parameter.
Hold effort constant within a conversation — changing it between requests invalidates prompt caching.
It's a behavioral signal, not a hard budget — at low effort, Claude still thinks on genuinely hard problems, just less.
Lower effort means fewer, terser tool calls — operations get combined and preambles vanish.
On Opus 5, effort tunes thinking volume, not reply length — if you want shorter answers, prompt for length. And at xhigh/max, thinking can't be disabled.
Where you set it: the API (output_config) and Claude Code. In claude.ai it mostly stays behind the curtain.

04 · Observing proposals Thirty tasks from your actual week Recommendations are this guide's judgment, applying the official guidance

Nothing matches — clear the search or switch category.

05 · The catalog Side by side Click a column header to sort

Model ↕	$ In/MTok ↕	$ Out/MTok ↕	Context ↕	Max output ↕	Latency ↕	Knowledge cutoff ↕	Thinking	Effort levels

* Sonnet 5 intro pricing — $2 in / $10 out — runs through Aug 31, 2026, then $3 / $15. Batch API discounts apply on top for all models.