//
$
pricing
//
$
pricing
Pay for runs, not seats.
Pay for runs, not seats.
Every plan includes the CLI, both SDKs and unlimited teammates. You only pay when a case actually runs.
Every plan includes the CLI, both SDKs and unlimited teammates. You only pay when a case actually runs.
Swipe the table to compare plans →
Swipe the table to compare plans →
Included runs / month
10,000
100,000
Unlimited
Then
Hard stop
$0.40 per 1,000 runs
Volume pricing
Rate limit
60 req / min
600 req / min
Custom
Parallel workers
4
64
256
Result retention
7 days
90 days
Custom
Teammates
Unlimited
Unlimited
Unlimited
SSO / SAML
Not included
Not included
Included
Self-hosted runners
Not included
Included
Included
Support
Community
Email, 1 business day
Shared Slack, 1 hour
Included runs / month
10,000
100,000
Unlimited
Then
Hard stop
$0.40 per 1,000 runs
Volume pricing
Rate limit
60 req / min
600 req / min
Custom
Parallel workers
4
64
256
Result retention
7 days
90 days
Custom
Teammates
Unlimited
Unlimited
Unlimited
SSO / SAML
Not included
Not included
Included
Self-hosted runners
Not included
Included
Included
Support
Community
Email, 1 business day
Shared Slack, 1 hour
Prices in USD, before tax. A run is one case against one model. Re-runs of unchanged cases are cached and free.
Prices in USD, before tax. A run is one case against one model. Re-runs of unchanged cases are cached and free.
//
diff
hobby → team
What you get the day you upgrade.
No migration, no new keys. The same CLI picks up the new limits on its next run.
//
diff
hobby → team
What you get the day you upgrade.
No migration, no new keys. The same CLI picks up the new limits on its next run.
+
Merge gate on every pull request
+
64 parallel workers (was 4)
+
90-day result history with diffs between runs
+
Self-hosted runners for private data
~
Rate limit 60 → 600 requests per minute
−
Hard stop at 10,000 runs
+
Merge gate on every pull request
+
64 parallel workers (was 4)
+
90-day result history with diffs between runs
+
Self-hosted runners for private data
~
Rate limit 60 → 600 requests per minute
−
Hard stop at 10,000 runs
//
?
questions
Questions we get on every sales call.
//
?
questions
Questions we get on every sales call.
What counts as a run?
One case, evaluated once, against one model. A 200-case suite tested on two models is 400 runs.
Do you train on our data?
No. Inputs and outputs are stored only for your retention window, encrypted at rest, and never used to train anything.
Can we run it without sending data out?
Yes. Team and Enterprise support self-hosted runners. Only pass/fail counts leave your network.
What happens if we go over on Team?
Nothing breaks. Extra runs bill at $0.40 per 1,000 and you get an email at 80% and 100% of the included runs.
What counts as a run?
One case, evaluated once, against one model. A 200-case suite tested on two models is 400 runs.
Do you train on our data?
No. Inputs and outputs are stored only for your retention window, encrypted at rest, and never used to train anything.
Can we run it without sending data out?
Yes. Team and Enterprise support self-hosted runners. Only pass/fail counts leave your network.
What happens if we go over on Team?
Nothing breaks. Extra runs bill at $0.40 per 1,000 and you get an email at 80% and 100% of the included runs.