Pricing
Start on a free trial, then pay for the usage you actually spend.
Free
20,000 credits, once
Includes:
- 20,000 credits when you verify your email — a trial, not a monthly allowance
- 1 knowledge base and 2 agents
- 1 seat
- Economy models, hybrid retrieval and reranking
- The agent canvas, with every step type
Starter
500,000 credits every month
Everything in Free, plus:
- 500,000 credits a month
- 3 knowledge bases and 5 agents
- One embedded chat widget on your own site
- Scheduled runs and outbound webhooks
- Credit top-ups when a month runs short
Pro
2,000,000 credits per person, monthly
Everything in Starter, plus:
- 2,000,000 credits per person each month
- Premium models — Claude Opus, GPT-5, Gemini Pro
- 10 knowledge bases and 20 agents, up to 25 seats
- Workspace API keys, to call an agent from your own product
- Connect your own database as a read-only source
Team
8,000,000 credits a month, 5 seats included
Everything in Pro, plus:
- 8,000,000 credits a month, shared across the workspace
- 5 seats included, $19 for each one after that
- Unlimited knowledge bases and agents
- Five embedded widgets
- Custom roles your workspace writes for itself
Enterprise
Usage agreed with you
Everything in Team, plus:
- Unlimited seats, invoiced rather than charged to a card
- Your own model endpoints, self-hosted ones included
- Private deployment and data-residency scoping
- Security review, a DPA and a named contact
Run out before the month does?
Top-ups never expire, and are spent only once the plan's monthly credits are gone. Available from Starter upward.
- 1,000,000 credits — $39
- 5,000,000 credits — $175
- 15,000,000 credits — $450
- Or name your own amount, from $10
Credits, not messages
One credit is one input token of a baseline model. Every model spends credits in proportion to what it costs, so switching models changes the number — not the unit you are counting in.
No surprise bills
When the balance runs out, runs stop cleanly and say so. Nothing overruns quietly, and nothing is charged that was not spent.
Change plan whenever
Upgrade, downgrade or cancel from the billing screen. Your renewal date, what you have paid and every invoice are on the same page.
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.”
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.”
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.”
IT Director
Financial services
“Our documentation is half Vietnamese, half English. One index handles both and an English question still finds the Vietnamese paragraph.”
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.”
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.”
Principal Engineer
Enterprise software
Pricing questions
One credit is one input token of a baseline model priced at $3 per million tokens. Every other model spends credits in proportion to what it actually costs — a cheap model spends a fraction of a credit per token, a frontier model spends several. Bought as a top-up, a million credits is $39; inside a plan they work out considerably cheaper.