Memory API
You pay for what you ingest and what you ask.
The people using your software never need a Revo account, so we count what the API does rather than how many people touch it. Every call returns its own cost under usage, so you can price a feature or cap a customer without instrumenting anything.
Usage
Metered
published rates, billed monthly
You pay for what you ingest, what you ask, and what the graph maintains. Every call returns its own cost under usage, so you can price a feature or cap a customer without instrumenting anything.
- Metered on ingestion, questions and resolved entities
- Included allowance, then per unit overage
- All four endpoints
- Answers with evidence and per call cost
- Multiple workspaces
Enterprise
Custom
annual agreement
For teams with a procurement process. Everything in Usage, plus the operational and contractual terms a platform team asks for before they put your memory in front of their own customers.
- Dedicated or in region deployment
- SLA and support terms
- DPA, retention policy and legal hold
- Audit logging
- Custom ontology for your domain
What counts
Three meters, defined precisely.
You should be able to work out the bill before writing any code. These are the three things we count.
Ingestion
One data point is one call to POST /ingest: an email, a transcript, a ticket, a note.
Ingestion is idempotent by content hash, so re-sending unchanged content costs nothing. A crashed backfill can resume by re-running the same loop.
Questions
One call to /recall or /answer.
We read a roughly fixed amount per question whether the record holds a hundred thousand tokens or ten million, so the bill does not grow with the history.
Resolved entities
The people, companies and projects the graph currently maintains for your workspace.
Metered on what the graph maintains rather than on bytes stored.
Why it stays flat
The bill does not grow with the history.
The usual alternative is to send the whole history to the model on every question, so cost climbs with every message you have ever stored. We read a roughly fixed amount per question whether the record holds a hundred thousand tokens or ten million.
23x
cheaper per question than sending 1M tokens of history, on the same model.
232x
cheaper at 10M tokens, where no production model can hold the context at all.
~96%
less context read per question at 1M tokens of history.
Expressed as multiples rather than per question prices, because what we charge is not what it costs us to run.
Tell us what you are building.
We answer these ourselves. Bring your volumes and we will model the bill with you on the call.