Pricing & limits
SyntheticBrew Cloud is priced by monthly active users (MAU) — the number of unique people who chatted with your agent in the last 30 days. With your own LLM key, chat turns are not a plan meter and inference is billed directly by your provider with no SyntheticBrew token markup. The shared onboarding key has a separate 50-turn rolling allowance described below.
SyntheticBrew Enterprise is scoped for customer-managed infrastructure. Its capacity, supported environments, onboarding, support, and service levels are defined for the deployment rather than by the Cloud plan table below.
| Plan | Monthly active users | Schemas | Knowledge-base documents | Support |
|---|---|---|---|---|
| Free | 100 | 2 | 25 | Self-service |
| Pro | 2,000 | 3 | 100 | |
| Business | 20,000 | 25 | 500 | Priority |
| Enterprise | Custom | Custom | Custom | Dedicated onboarding |
Pro is $49/mo ($490/yr — two months free). Business is $199/mo ($1,990/yr). Enterprise is quoted per deployment — contact us.
What counts as an active user
Section titled “What counts as an active user”A monthly active user (MAU) is a unique end-user who sent at least one message to your agent within the last 30 days. This is a rolling window, not a calendar month or billing period — there is no reset day: a user counts as active for exactly 30 days after their last message and then ages out. A single user is counted once no matter how many messages they send, so a chatty user costs the same as a one-message user.
- Authenticated end-users are identified by their user id.
- Anonymous widget visitors are counted once each via a persistent visitor id stored in the browser, so a returning visitor within the same window is not double-counted.
MAU measures distinct people, not conversations or messages.
How limits behave
Section titled “How limits behave”Limit enforcement differs by plan so that a free deployment can’t accidentally exceed its allowance while a paying customer is never cut off mid-service:
- Free plan — hard cap. Once your rolling 30-day count reaches 100 active users, new users are blocked from starting a chat until the count drops back below the limit (users age out of the window 30 days after their last message). Users who are already chatting keep their sessions; existing conversations are never interrupted.
- Paid plans — soft cap. Service continues past the included MAU allowance — your users are never blocked mid-period, and overage is never billed automatically. Exceeding the allowance only triggers an upgrade prompt in the dashboard; if your traffic has outgrown the plan, move up a tier or contact us for a custom allowance.
The schema and knowledge-base document limits are provisioning limits: you can create up to the plan’s number of schemas and stored documents. Agents are not capped as a separate plan dimension. Chat turns and reasoning steps are not tier-differentiated plan meters when you use your own key; the shared platform key’s onboarding allowance is enforced through the usage-limit mechanism.
Knowledge Graph provisioning has its own current Cloud defaults:
| Plan | Bundles | Total entities | Per entity | Per bundle |
|---|---|---|---|---|
| Free | 1 | 200 | 50 KiB | 5 MiB |
| Pro | 3 | 2,000 | 100 KiB | 10 MiB |
| Business | Unlimited bundles | 20,000 | 100 KiB | 10 MiB |
| Enterprise | Defined by the order form/operator policy | Defined by the order form/operator policy | Defined by the deployment | Defined by the deployment |
These are deployment quotas, not the generated graph tool’s request bounds. For example, list and batch-get calls still accept at most 500 items/IDs per request even when the deployment can store more entities. Custom Cloud agreements can override the plan counts.
Bring your own key (BYOK) — everywhere
Section titled “Bring your own key (BYOK) — everywhere”Every Cloud plan supports BYOK. Enterprise can enable the same feature under operator policy. Configure a provider key in Admin, or pass it per request with the BYOK headers. Inference then runs on your key at your provider’s price without a SyntheticBrew token markup.
Every Cloud plan — Free, Pro and Business alike — also includes a shared LLM allowance of 50 platform-funded chat turns per rolling 30-day window on SyntheticBrew’s key, so you can onboard and run an agent before wiring up your own provider. Beyond that allowance, switch to BYOK for unlimited turns at your provider’s cost. The allowance is a convenience, not a per-plan differentiator — it is the same on every tier.
Attribution on free plans
Section titled “Attribution on free plans”Free-plan agents include a “Powered by SyntheticBrew” attribution:
- the agent is instructed via its system prompt to identify that it’s powered by SyntheticBrew — best-effort, since how consistently the agent follows the instruction depends on the model, and
- a deterministic “Powered by SyntheticBrew” badge is shown on the embeddable chat widget.
Upgrading to Pro or Business removes both the system-prompt instruction and the widget badge. Enterprise plans are unbranded by default.
What’s next
Section titled “What’s next”- BYOK — bring your own model key on any plan
- Usage limits — operator-configurable turn and step controls
- Enterprise on-premises — customer-managed private deployment