Pricing
Plans and credits
Every plan uses several AI models from different companies that check each other. Higher plans add flagship models, full control and more usage.
Self-serve plans
Billed monthly in US dollars. Start on Free; no card needed.
Free
Try the council
$0/ month
60 credits a month, no extra usage
- Smart, Quick check and Standard depths
- A fixed council of four models from different companies
- Checked statements with highlighted sources
- Full details and audit record for every answer
- 60 credits a month (about 6 Standard questions)
- Up to 5 files of 10 MB per question
Pro
Most popularFlagship models, and every model and algorithm setting is yours
$49/ month
200 credits a month, more on request
- Everything in Free
- Flagship council (Claude Opus, GPT-6.1 Sol, Grok 4.7, Kimi K3)
- Thorough and Full report depths
- Choose the model for every seat, effort and answer length
- Algorithm settings: checking rounds, verdicts per point, thresholds
- 200 credits a month (more on request)
- Up to 20 files of 50 MB per question
- Human review of disputed points
Pro Max
Your own councils and long documents
$199/ month
800 credits a month, more on request
- Everything in Pro
- Build and save your own councils
- Collections: ask across hundreds of documents
- Advanced retrieval settings for very large documents
- Calibrated “Confirmed” results with a measured error rate
- API keys for your own integrations
- 800 credits a month, 4× Pro (more on request)
- Up to 100 files of 200 MB per question
- Priority runs on reserved capacity
Teams & Enterprise
For organisations that need central control. Talk to us about:
- Single sign-on (SSO) and SCIM user provisioning
- Longer audit-record retention
- Bring your own key (BYOK) for encryption
- Allowed-vendor and data-residency rules
- Invoicing and a signed DPA
Usage
Credits per question
A credit is the unit of usage. Deeper checks use more models and rounds, so they cost more.
| Depth | Credits | Typical time | What happens | Plans |
|---|---|---|---|---|
| Smart | 3 or 10 | 20 s – 5 min | Two models answer first; if they disagree, the full council is called in. Charged 3 credits if the fast path answers, 10 if the full council is needed. | All plans |
| Quick check | 3 | about 30 s | Two models from different companies answer and their points are compared. | All plans |
| Standard | 10 | 2 – 5 min | Several models answer on their own, check each other's points against your sources, and an editor writes the answer. | All plans |
| Thorough | 25 | 5 – 15 min | More models, more checks per point, more rounds and a dedicated checker on every statement. | Pro, Pro Max |
| Full report | 25 | 8 – 25 min | Each model writes a complete report; the best parts are merged and every statement is fact-checked. | Pro, Pro Max |
Smart routing
Why Smart mode costs less
Two models answer first. The full council only runs when they disagree or the workspace is high-risk.
Every statement in both paths is still quoted and labelled.
Fast when models agreeTwo models from different companies answer first. If their answers match, you get the answer in about 20 seconds for 3 credits.
The full council when it mattersIf they disagree, or your workspace is marked high-risk, all four models answer and check each other: 10 credits.
$0.24 on averageSmart mode's average model cost on the 483-question locked test: $0.236, under the preset limit of half the Standard council ($0.279). Long free-text questions mostly take the full council.
Design partner programme
3 places for legal, audit or compliance teams
3 months of Pro Max free, in exchange for feedback while we shape the product with you.
FAQ
Questions about pricing
What is a credit?
What happens when I run out?
Do unused credits roll over?
Do you train models on my documents?
Can I change or cancel my plan?
Which models are in the council?
Are prices final?
Buying for a legal, audit or compliance team?
Book a 30-minute call. We walk through a real run on a document like yours and answer security and procurement questions.