Pricing that shows its work.
Four tiers. Every query is billed in credits, at our provider cost plus 30 percent, and shows what it cost on the answer it paid for. Spending is prepaid; nothing can bill past credit you bought.
Free
For finding out whether this works on your questions.
- 25 papers in your library
- 5 corpus questions a month
- 2 full synthesis runs, total
- The included 13,900-paper searchable corpus
- No card required
The synthesis runs are the real product. Two is enough to judge the output on a topic you know.
Limits and perks
in this tier
- Library capped at 25 papers
- 5 corpus questions a month
- 2 full synthesis runs, total
- An honest bail does not count against the two
not in this tier
Included monthly creditMCP access for your agentsPriority Deep runsMore than one seat
Pro
For one person doing real research.
- 1,000 papers in your library
- No cap. Credit-based: about 36 runs a month on the included 15,000 credits at Standard rates, or about 197 lighter corpus questions. Budget-tier runs cost a fraction of that.
- Per-query cost and grounding shown on every answer
- Cost preview before every heavy run; nothing spends past your balance
- MCP access at launch: your agents can search the corpus and ask grounded questions
Limits and perks
in this tier
- Library capped at 1,000 papers
- Runs bounded by the 15,000 credits included each month
- Single seat
not in this tier
Priority Deep runsThe 10,000-paper libraryMore than one seat
Ultimate
For one person who runs it hard.
- 10,000 papers in your library
- No cap. Credit-based: about 108 runs a month on the included 45,000 credits at Standard rates, or several hundred lighter corpus questions.
- 45,000 credits included monthly
- Deep runs get priority in the queue
- Higher API rate limits and more keys for your agents
- Per-query cost and grounding shown on every answer
- Single seat
Limits and perks
in this tier
- Library capped at 10,000 papers
- Runs bounded by the 45,000 credits
- Deep runs get priority in the queue
- Single seat
not in this tier
More than one seat
Team
For a desk.
- 10,000 papers in your library
- Five seats
- 60,000 credits included monthly
- Everything in Pro, on every seat
Set up per desk, by contact.
Limits and perks
in this tier
- Library capped at 10,000 papers
- Runs bounded by the 60,000 credits
- Five seats
- Everything in Pro, on every seat
not in this tier
Priority Deep runs
Measured, per tool.
One row per tool: what a single run costs you, in credits. The billed price includes a 30 percent margin over our provider cost.
| tool | billed credits |
|---|---|
| Corpus question | ~76 credits |
| Disagreement map | ~135 credits |
| Topic recommendations | ~126 credits |
| Strategies with adversarial review | ~420 credits |
All four are billed figures from real runs on production, captured 2026-08-26 (runs 58, 60, 61, 59). The billed price includes a 30 percent margin over our provider cost.
The only rate in the product.
Every query is billed in credits, itemized, and shown on the answer it paid for. The billed price is our provider cost plus 30 percent. That is the only rate. The tiers decide how much credit is included.
Pro includes 15,000 credits each month, Ultimate 45,000, and Team 60,000. At the measured Standard run cost, 15,000 credits is about 36 runs a month and 45,000 about 108. Budget-tier runs cost a fraction of that.
Spending is prepaid. Every heavy run shows its estimated cost before it starts, and a run your balance cannot cover does not start. You get a notice when credit runs low. There is no overage and no mechanism to bill past credit you already bought.
If a month runs heavy, a booster adds 25,000 credits for $25, paid up front, applied immediately.
Included credit does not roll over. The meter resets with your billing month.
The subscription is the library. The credits are the fuel.
Your $39 a month is not a pile of compute with a markup on top. It is standing access to the thing the compute runs on. A corpus of roughly 15,000 quantitative-finance papers, kept current. Retrieval that finds the handful bearing on your question and reads them in full. A workspace that holds your projects, your theses, your runs. And the tools that turn all of it into an answer with its cost on it: corpus questions, strategy runs with adversarial review, disagreement maps.
The credits meter the compute inside that. They are the fuel. The included credit runs the tools each month. The subscription is what makes there be something worth running them on: a library that exists and stays current whether or not you run a heavy month. That is what you are paying for.
What counts as a synthesis run?
Any of the heavy tools: a research program, strategies with the adversarial review, or a combiner run. A corpus question is lighter and counted separately on Free. On paid tiers neither has a per-run cap; the bound is your credit balance.
What happens when my credit runs out?
Paid queries stop, with the numbers shown, and work in progress completes. A booster tops the balance up. Nothing can bill past credit you already bought. Automatic top-up at a threshold you set is on the roadmap.
What if a run fails, or comes back saying the evidence is not there?
A technical failure never consumes a run and never bills you. On the Free tier, a run that ends in an honest bail does not count against your two. The two runs exist so you can judge the synthesis on questions you know.
Which model does it use?
Frontier models from Anthropic and OpenAI. Each answer shows the credits it cost.
Can I bring my own API key?
Not yet. It is on the roadmap. All usage runs on included and metered credit.
How do I get the Team tier?
Write to mstatha@outsample.com and we set your desk up directly. Billing starts when your seats do.
Can I cancel or change plans myself?
Yes, from the billing portal, immediately. Annual plans are refunded pro rata where the law requires it and case by case otherwise; write to us.
Do you train on my library or my queries?
No. Your uploads and your questions are yours.
Is there a trial?
The Free tier is the trial and it does not expire. Two full synthesis runs is enough to judge the output on your own questions.
No card. If the output is not worth $39 to you, the Free tier already told you so.