Get started
one free plan

Pick a plan. Pay for tokens.

Three plans, one of them free. Each comes with a monthly pack of tokens. Need more? You roll straight onto pay-as-you-go — billed per token, with spending limits so there are no surprises.

Start building for freeTalk to our Sales team
Free
$0forever
free, forever

Try Faustine on real work — no card required.

1M tokensincluded every month
  • 1 live assistant
  • Prompt caching built in
  • Spending limits
  • Community support
Start free
Recommended
Pro
$89/mo
billed yearly

Ship an assistant your users rely on.

25M tokensincluded every month
  • Unlimited assistants
  • Prompt caching + Batch API
  • Pay-as-you-go past your pack
  • Spending limits per assistant
  • Email support
Start Pro
Scale
$449/mo
billed yearly

High volume, with controls and support.

150M tokensincluded every month
  • Everything in Pro
  • Higher rate limits
  • SSO & team roles
  • Usage analytics
  • Priority support
Start Scale
Enterprise
Custom
Let’s scope it together

Custom volume, controls and compliance.

Custom volumescaled to your usage
  • Everything in Scale
  • Custom token volume & limits
  • SSO / SAML & SCIM
  • Dedicated support & SLA
  • VPC or on-prem option
Contact us

Token packs cover input + output across any model · unused tokens reset monthly · cancel or switch anytime.

Pay as you go

Past your pack, just pay per token.

Go over your monthly pack — or skip the plan entirely — and you only pay for the tokens you use, metered by the model. No seats, no minimums.

ModelInputOutputCache write5-minCache readhitBatchin / out
Faustine Opus 4.8DefaultMost capable · default$5.75$28.75$7.19$0.58$2.88 / $14.38
Faustine Sonnet 4.6Balanced speed & smarts$3.45$17.25$4.31$0.35$1.73 / $8.63
Faustine Haiku 4.5Fastest & most efficient$1.15$5.75$1.44$0.12$0.58 / $2.88
Faustine Fable 5Frontier reasoning$11.50$57.50$14.38$1.15$5.75 / $28.75

All prices in USD per 1M tokens. Cache reads are billed at ~10% of input; the Batch API runs at 50% off for non-urgent work.

Built-in efficiency

Token compression, on by default.

Before you’re billed for a single token, Faustine squeezes the request — reusing context that repeats, pruning stale tool output, and summarizing long conversations on the fly. Same answers, a fraction of the tokens, with nothing to configure.

  • Prompt caching. Repeated context is reused across requests instead of re-sent and re-billed.
  • Context pruning. Stale tool results and dead branches are dropped before they cost you.
  • Live compaction. Long histories are summarized automatically as the conversation grows.
Set spending limits
Cap spend per day, per month or per assistant. When you hit the limit, Faustine stops — no surprise bills, no overage.
Prompt caching
Reuse the stable parts of every prompt. Cached reads cost a fraction of fresh input, so busy assistants get cheaper the more they run.
Batch API · −50%
Send non-urgent work — backfills, bulk classification, overnight jobs — at half the per-token price, returned within 24 hours.
One token meter
No per-seat fees and no AI infrastructure to run. You pay for tokens; Faustine handles the agents, evals and model ops.
Questions

The pricing, plainly.

What’s a token pack?
Every plan includes a monthly allowance of tokens — the words your assistant reads and writes — that you can spend on any model. It resets each month.
What happens when I use it all?
You keep going on pay-as-you-go: past your pack you’re billed per token at the rates below. The Free plan simply pauses when its pack runs out — upgrade anytime.
Can I cap how much I spend?
Set hard spending limits per day, per month or per assistant. When a limit is reached, Faustine pauses automatically — so a spike can never blow past your budget.
Can I switch plans or models?
Anytime, and changes are prorated. Faustine also picks the right model per task and rolls forward as better ones ship — your code never changes.

Start free. Today.

Connect your app, switch on the actions you want, and ship the assistant on the free plan. Upgrade only when you outgrow it.

Start free →Talk to us
No card · no minimums · no lock-in