Pricing
An execution is one test case run against your prompt, LLM judging included. Every plan includes unlimited criteria, test cases, and version comparisons.
Free
Kick the tires. No card required.
$0 / month
- 2 prompts
- 50 eval executions / month
- Unlimited criteria & test cases
- Version comparison
Pro
Most popularFor builders shipping prompts to production.
$29 / month
- Unlimited prompts
- 2,000 eval executions / month
- Unlimited criteria & test cases
- Version comparison
- CSV test-case import
Team
For teams that eval every day.
$99 / month
- Everything in Pro
- 10,000 eval executions / month
- Priority support
Frequently asked questions
What counts as an execution?
One test case, run once, against one prompt version — including the LLM-judge pass that scores it against all your criteria. A run of 10 test cases uses 10 executions.
Do I need my own Anthropic API key?
No — model usage is included in your plan. Executions are capped per month to keep that sustainable.
What happens when I hit my monthly cap?
Runs pause until the next calendar month, or you can upgrade for a bigger allowance. Nothing is deleted; your prompts, versions, and history stay put.
Can I cancel anytime?
Yes — manage or cancel from the billing page in one click. You keep paid features until the end of the billing period, then drop to the Free plan.