Pricing

Start free, then scale seats and usage as adoption grows.

Free

$0

Includes:

  • 1 knowledge base, up to 200 documents
  • 500 chat messages per month
  • Standard models and hybrid retrieval
  • 1 seat

Pro

$29/month/person

Everything in Free, plus:

  • Unlimited knowledge bases and documents
  • 10,000 messages per person per month
  • All models, including reranking and long context
  • Agents with tools, scheduling and the API
  • Retrieval trace and answer evaluation
  • Usage top-ups available

Team

$59/month/person

Everything in Pro, plus:

  • Permission-aware retrieval synced from each source
  • Shared Agent Skills and workspace rules
  • SSO (SAML, OIDC) and SCIM provisioning
  • Audit log and per-project usage reporting

Enterprise

Custom

Everything in Team, plus:

  • Private cloud (VPC) or on-premise deployment
  • Bring your own model endpoints and vector store
  • Custom connectors and data-residency guarantees
  • Security review, DPA and a named success engineer

Usage, not seats alone

Seats cover access; messages and agent runs are metered. The dashboard shows both as they accrue.

No surprise bills

Hit the monthly cap and runs pause cleanly rather than silently overrunning your budget.

Move plans anytime

Upgrade, downgrade or top up usage per person. Annual billing saves roughly 20%.

From the teams running it every day

We had three separate search tools and none of them could answer a question. Ragenta replaced all three in a month, and the citations are the reason people actually trust it.

HO

Head of Operations

Logistics, 900 staff

Support deflection went from a slide in a strategy deck to a number on a dashboard. The retrieval trace is what let us debug it ourselves instead of filing tickets.

CS

Customer Support Lead

B2B SaaS

Permission-aware retrieval was the whole deal for us. Legal would not sign off on anything that indexed HR files into one bucket.

ID

IT Director

Financial services

Our documentation is half Vietnamese, half English. One index handles both and an English question still finds the Vietnamese paragraph.

EM

Engineering Manager

Fintech, Ho Chi Minh City

The agent does not just retrieve — it decides what to look up next. Watching it re-query after a weak first result was the moment this clicked for the team.

HO

Head of Data

Healthcare group

We swapped the underlying model twice in a quarter without touching a single prompt. That flexibility is worth more than any single model benchmark.

PE

Principal Engineer

Enterprise software

Pricing questions

One question and its answer, including the retrieval and any tool calls the agent made to produce it. A multi-step agent run counts as one message plus its tool usage.

Put an agent on your knowledge today

Book a demo