skip to content
fizzgig
sign in
// product
code auditdetect what shippedbrand and reachsoonlift qualityperfect memorysoondecision graph
// build better
sourdough startersproject kicks-off in 1 prompt
// resources
pricingdocsblogabout
sign inrequest access →
// pricing

what you pay for is headroom, not access.

free users get the same product as pro users. they just hit a wall sooner. tokens meter how much input you send to the audit — the more you build, the more you use. one tool call ≈ one scan ≈ a few KB to a few MB of code.

// free

free

£0forever

for trying the kit. one project, a few scans. see what the audit catches that your other linters missed. when you hit the wall, you'll know if it's for you.

1 MB of input / month
≈ one full scan on a real project
  • +every code audit check
  • +one mcp install, every editor
  • +mailing list + roadmap input
  • −brand and reach (coming soon)
  • −perfect memory (coming soon)
start free →
for the side hustle
// vibe hobby

vibe hobby

£5/ mo + VAT

for the vibe coder building a small side hustle. prototyping the next idea on a friday night, shipping the weekend project, playing with what's possible. enough headroom to keep your code honest without ever thinking about scans.

10 MB of input / month
≈ 1.5 full code-audit sweeps, or ~10 individual tool scans, before the wall
  • +every code audit check
  • ++£3/mo per add-on leg (brand and reach, perfect memory)
  • +soft warnings at 80% + 95%
  • +annual: 12 months for the price of 10
// vibe pro

vibe pro

£15/ mo per leg + VAT

for super amateurs coding through the night, indie founders shipping multiple projects, and pro teams building things that need to actually work. all three legs together, pooled tokens, every tool every day.

1 GB of input / month per leg
≈ daily full-sweep on one project = 17% utilisation; daily across four projects ≈ 68%
  • +pick a leg, or all three
  • +pooled tokens across the trio
  • +priority queue + early access to new tools
  • +annual: 12 months for the price of 10
// the trio

all three legs of vibe pro.

£42/ mo inc VAT
(£35 / mo ex VAT — save £10 vs single-leg × 3)

code audit + brand and reach + perfect memory. pooled tokens across all three legs. one subscription. one bill.

the answer to life, the universe, and everything.
don't panic — bring a towel.

// how tokens work

tokens = input bytes.

// 1
1 token = 1 KB of input

we count the bytes your AI editor sent us — the file contents you asked us to scan. small scans round up to a single token, so even a tiny check costs something.

// 2
combo tools charge the parent

launch_checklist fans out to 22 sub-tools internally. the token charge is the sum of all sub-tool inputs, charged on the parent run. your dashboard breaks down where the tokens went.

// 3
hit the wall? upgrade prompt.

when you hit your monthly cap, the next tool call returns a structured upgrade nudge — surfaced verbatim by your AI editor. no surprise bills, no pay-as-you-go gotcha. soft warnings at 80% + 95%.

// 4
we never see raw input

tokens are byte counts. the audit-log row stores how many bytes you sent + which slots you filled + the findings — never the raw source. privacy default, not a configuration.

// savings

two ways to pay less.

// annual

12 months for the price of 10.

pay annually and get ~17% off — that's two months free on any tier. the trio annual = £350 ex VAT (£420 inc VAT). cancel anytime, refund prorated.

// student

30% off for students.

verified .edu / .ac.uk email gets 30% off any paid tier. stacks with annual. coupon applied automatically at checkout. for actual students — not a coupon-farming exercise.

// faq

questions you might have.

what counts as a token?
1 token = 1 KB of input you sent to a tool. small scans round up to 1 token. for combo tools (launch_checklist) the parent run is charged the sum of all sub-tool inputs.
what happens when i hit the cap?
the next tool call returns a structured upgrade prompt your AI editor surfaces verbatim. no surprise bills. soft warnings at 80% + 95% via dashboard banner + email so you see it coming.
can i use fizzgig with claude code?
yes. it works in any mcp-compatible client: claude code, cursor, windsurf, lovable, bolt, replit, zed (beta).
do you see my code?
we never persist raw input. each tool returns a structured result; the audit-log row stores byte counts, which input slots were filled, and the findings (with line context already redacted) — never the raw source.
can i mix legs and tiers?
yes. hobby + £3/mo per add-on leg (brand and reach or perfect memory) is the most flexible path. pro is single-leg or trio. when brand and reach + perfect memory ship at june launch, hobby users can add either as a £3/mo bolt-on.
is there a self-hosted version?
not yet. roadmap: H2 2026. enterprise tier is currently deferred until indie funnel unit-economics are proven.
what about pay-as-you-go top-ups?
deferred until we see how many users hit their cap mid-month. for launch: hard cap with upgrade prompt, no overage billing. simpler model, no surprise bills.
why £42 for the trio?
we'd hoped you'd notice. £42 inc VAT works backwards to £35 ex VAT — about a £10 discount vs three single-leg Pros. the number itself is the answer to life, the universe, and everything. don't panic.
fizzgig

the fluffy guardian of vibe-coded apps. growls at insecure code so you don't have to.

all systems operational

product

code auditbrand and reach (soon)perfect memory (soon)pricingdocschangelog

community

sourdough startersdiscord (soon)github (soon)x / twitter (soon)rss (soon)

company

aboutcontactterms (soon)privacy
© 2026 fizzgig labs.
v1.4.2 · 2026-05-01