Free
Explore your first workflows.
$0/ month
100 runs each month
$0 per run · $15 top-up value
Get started for freeAll features · Unlimited teammates
PRICING
Start free.
Scale your evals.
Every feature from day one. Choose the monthly run
allowance that fits your work.
Platform runs only. Model inference is separate.
Use your own API keys or a supported subscription.
Pro
For everyday evalsMake evals part of development.
$20/ month
300 runs each month
$0.067 per run · $40 top-up value · Save $20/month
Get startedAll features · Unlimited teammates
Ultra
Run more workflows, more often.
$60/ month
1,000 runs each month
$0.06 per run · $120 top-up value · Save $60/month
Get startedAll features · Unlimited teammates
INCLUDED FROM DAY ONE
The whole platform.
For your whole team.
All four modules
Evaluate your product, your custom agent, the agent experience, and your own benchmarks.
Room for the team
Unlimited members at no extra cost. Everyone draws from the same shared run pool.
Work through your agent
Full web app, CLI, and MCP access. Design, run, and investigate through one connection.
MORE RUNS WHEN YOU NEED THEM
Top up.
Keep going.
Add runs without changing your plan.
Top-up runs never expire.
| Runs | Price | Per run |
|---|---|---|
| 25 | $5 | $0.20 |
| 100 | $15 | $0.15 |
| 300 | $40 | $0.133 |
| 1,000 | $120 | $0.12 |
THE DETAILS
Know what you’re running.
What counts as a run?
One run is one agent attempt on a task under a treatment. Errored or cancelled runs do not count against your organization's pool. A completed run still counts when its rubric verdict is fail.
What does the price cover?
Runs cover Oqoqo platform fees for durable experiment workflows and cloud infrastructure. Model inference is separate. Use your own API keys or subscriptions. Oqoqo may limit use to keep capacity fair.
Do unused runs carry over?
Monthly plan runs reset each billing period. Purchased top-up runs never expire.
Can the whole team use one plan?
Yes. Add unlimited organization members. Everyone draws from the same shared run pool.
Your next eval starts
with your coding agent.
Give it the framework and infrastructure
to design, run, and analyze your evaluations.