unbiased ai

Hitting limits? Here is the arithmetic.

Subscription caps are a budgeting device: the plan meters you by session windows and weekly ceilings so the flat fee stays flat. Credits invert it: no reset schedule, your bill just tracks your work. The question is what your work costs, so we metered it.

or match your spend in credits

One working week, two billing models

Schematic, not a measured quota: where the wall lands varies by plan and week. That there is a wall is the design.

Provider limits change often and are rarely published precisely; treat any specific cap you read anywhere as dated. That volatility is what the alert list below is for.

One real agent session, metered

Numbers about caps are usually vibes. This is a bill: one Claude Code working session on API credits, five calls, priced by the provider meter.

the whole session on API credits: five calls, real work, actual bill
cheaper with prompt caching on, because agent work is mostly re-reading
tokens read vs written in that session, which is why caching moves the bill so much
weekly resets on credits. Heavy week, heavy bill; quiet week, quiet bill

Session ledger, replayed

Real bill
  • API call 1metered
  • API call 2metered
  • API call 3metered
  • API call 4metered
  • API call 5metered
Session total call it $0.59

Caching on, as the session really ran. The re-read discount is already in this number.

Prompt caching on

Flip it to price the same five calls without the cache discount.

Each call bills tokens in and tokens out; the meter does not care what the call did. Call-by-call amounts are in the pricing writeup; this page keeps the sum.

Why caching moves this bill

An agent session reads far more than it writes: context, files, earlier steps, again on every call. This one read 78 tokens for every 1 it wrote. Caching discounts exactly that re-reading.

, the shape of agent work.

What a task costs when it is metered

One identical prompt, run the same day, billed on metered dashboards. Not a benchmark, a receipt: this is the spread a meter sees for the same job.

Fable 5
Opus 5
Opus 4.8
Sonnet 5
Pareto
Haiku 4.5

Second task, a game build, so you know the spread is not a one-off:

Fable 5
Pareto

Meters bill verbosity too: on an identical task at identical rates, . Same prices, bigger bill.

Your week in credits

Weekly bill = tasks per day . Slide your workload.

10
  • Fable 5 $10.23$0.1462 per task
  • Opus 5 $8.11$0.1158 per task
  • Opus 4.8 $5.07$0.0724 per task
  • Sonnet 5 $2.87$0.0410 per task
  • Pareto $1.37$0.0196 per task
  • Haiku 4.5 $1.13$0.0162 per task

Your tasks are not this exact task; the shape is the point, not the penny. A heavy week costs more and finishes. A capped week just stops.

The rate card after the cap

Since July 7, 2026 the frontier model is credits-only, so this is the menu. Per million tokens, provider list.

API credit rate card, July 2026, prices per million tokens
Model Notes
Fable 5$10$50API only since Jul 7, 2026
GPT-5.6 Sol$5$30output 6x input
Opus 5$5$25launched Jul 24, 2026, same card as Opus 4.8
Opus 4.8$5$25
Kimi K3$3$15cache-hit input $0.30; API live Jul 16, 2026
Terra$2.50$15
Sonnet 5$2$10until Aug 31; $3 / $15 from Sep 1
Luna$1$6

Output runs 5 to 6x input on every card here.

The cap timeline so far

Three moves, one direction. Hover or tab across the strip.

Fable 5 leaves Claude subscription plans. The frontier model becomes API-only: usage credits at $10 in and $50 out per Mtok. The cap conversation becomes a meter conversation.

The direction is one-way: the heaviest users get metered first. Planning around caps means re-planning every time they move.

Limits change without changelogs. Here is the log.

Kept by hand, dated, source-checked. The alert list gets each new entry before this page does.

SUMMER 2025Weekly usage limits arrive on Claude subscription plans.
SUMMER 2025Session windows land: usage meters in 5-hour blocks inside the week.
JUL 7, 2026Fable 5 leaves subscription plans entirely: API-only, usage credits, $10/$50 per Mtok.
NEXT ENTRYLands in subscriber inboxes first. That is the whole service.

SAMPLE ALERT Jul 7, 2026: Fable 5 left Claude subscription plans. API-only, usage credits, $10 in / $50 out per Mtok. What it does to the math: the heaviest tier now meters, so a heavy week is a bill, not a wall. Full record: unbiased.ai/limits/

One email when a major provider changes usage limits or plan terms: what changed and what it does to the math. Price moves have their own dated record and list on the AI price tracker.

One request in, one answer out: the blend picks per request, so you skip this choice entirely.

Get your credits matched