Jump To Category Page

Jump To Representative Detail

Models Category View

Model inventory should show which model lanes concentrate spend, boundary exposure, and session shape before it behaves like a pricing sheet.

The category page should explain how model choice changes consequence: who selects it, what workflows it powers, and whether spend or cache behavior is drifting.

Use This Page When Asking

Which model lanes matter because of cost, work shape, or external-provider consequence?

Representative Detail

claude-opus-4-6

Open representative detail

Model lanes

A few dominate spend

Top spend lane

claude-opus

Premium work cluster

Cache outlier

62%

Worth reading beside spend

Provider spread

Anthropic-led

One main external boundary

Why This Page Exists

This category page should help the reviewer decide what matters in models before the raw table takes over the reading experience.

What This Page Should Make Obvious

The reviewer should know what is routine, what is risky, and what deserves the next click.

Model choice is a behavior signal

A model lane tells you about expected work shape, cost, and how much company context is likely to move outward.

Keep spend beside usage shape

Cost without users, agents, and cache context is harder to interpret correctly.

Preserve provider and boundary context

Model inventory should stay connected to the external provider surface, not drift into abstract token stats.

Fastest Drill Paths

The next clicks should feel obvious and intentional.

Premium coding model lane

A small number of sessions drive a disproportionate share of spend and context movement.

Open representative detail

Best first click for understanding model consequence.

Raw pricing and session table

Exact cost, tokens, and recent session rows still matter after the framing layer.

Open c6 raw list

The refined page should lead into the raw ledger, not replace it.

Model-Centered Topology

A model map should pair usage footprint with spend, cache efficiency, and the workflows it powers.

Useful per model: provider/family, who uses it, which agents and keys select it, what session shapes it appears in, and whether spend or cache behavior is changing.

Model

claude-opus-4-6

Premium model concentrated in a small set of high-cost sessions.

5 sessions · $38.10 total

Provider

Anthropic

Family

claude-opus

Cache hit rate

62%

Spend posture

top spend model

Primary Consumers

Who selects this model most often.

3 nodes

bob@company.comtop user

Cursor v0.42.0top agent

sk-ant-...A3F2credential

Session Shape

The type of work this model is serving.

3 nodes

long coding sessions44 turns max

high token outputpremium spend

cache reads62%

Comparative Context

How it differs from adjacent models.

3 nodes

claude-sonnet-4-6volume leader

claude-haiku-4-5CI / cheap path

gpt-4orare fallback

Watch For

The questions worth asking before cost spikes.

3 nodes

cost slope$38.10 total

new provider mixrouting shift

cache dropefficiency loss

c6 Raw Reference

c6 shape: model ledger ranked by family, provider, sessions, spend, and cache behavior.

Models

Premium lane

claude-opus-4-6

Highest spend

$12.4k

Cache hit baseline

71%

Why Keep The Raw Ledger

c12 should still flow back into the raw inventory model. This page frames the question and likely answer; the raw table proves it.

Open c6 Raw List

Use the original category ledger for exact rows, counts, and timestamps.

Open c6 raw list

Raw Model Inventory

Model id, family, provider, sessions, spend, and cache hit.

Model ID	Family	Provider	Sessions	Total cost
claude-sonnet-4-6	Sonnet	Anthropic	31	$8.20
claude-opus-4-6	Opus	Anthropic	8	$12.40
claude-haiku-4-5	Haiku	Anthropic	4	$0.82