Skip to content
Wetel Docs

Pricing & Plans

Wetel is under active development, and its pricing model is still evolving. This page describes what’s real today and is explicit about what isn’t built yet — see Getting Started to start building in the meantime.

How plans work today

Section titled “How plans work today”

Every tenant on Wetel is assigned a plan tier. Right now, a plan tier controls resource quotas — how much you can store and index — not a token or API-call quota. There is no per-request billing tied to your plan today; the tier simply determines the ceilings on the resources described below.

The three tiers

Section titled “The three tiers”

Wetel currently defines three plan tiers:

  • DEV — intended for local development, prototyping, and evaluation.
  • PRO — intended for production workloads at moderate scale.
  • ENTERPRISE — intended for larger production deployments with higher resource ceilings.

What differs between tiers

Section titled “What differs between tiers”

The concrete axis that differs between tiers today is knowledge base capacity — specifically:

  • the maximum number of knowledge bases a tenant can create,
  • the maximum number of chunks a tenant can index across those knowledge bases, and
  • the maximum total storage (in MB) a tenant can use for knowledge base content.

Each tier has its own limit on each of these three axes, enforced server-side. We’re intentionally not publishing the exact numbers here — they’re still being tuned as the platform matures, and we don’t want this page to go stale the moment they change. If you need to know your tenant’s current limits, or want them raised, contact the team directly.

What’s not built yet

Section titled “What’s not built yet”

To be direct about where things stand:

  • There is no public rate card. We don’t yet publish a per-call or per-token price for API usage.
  • There is no usage-based billing. Nothing on Wetel today meters your API calls against a dollar amount.
  • There is no credit or wallet system. You cannot pre-purchase usage credits.

Per-call cost tracking exists as internal infrastructure to help us understand usage patterns, but it isn’t exposed to customers as pricing, and there’s no committed timeline for when it will be. The closest thing to a documented per-call constraint today is the embed() API’s rate limit — it’s a rate limit, not a price, but it’s the general direction usage-based pricing would eventually build on.

Getting current plan details

Section titled “Getting current plan details”

Since self-serve plan comparison and checkout don’t exist yet, the right way to get a plan set up — or to ask about tier limits for your use case — is to contact the team directly rather than expecting a pricing calculator on this site. See Troubleshooting for contact routes, or refer to the API Reference and Authentication docs to start integrating while plan details are being finalized.

Section titled “Related”