Pricing
Built for teams who ship AI at scale
14-day free trial on all plans. 50 eval credits included. No credit card required. Overage billing available on all tiers.
Team
per workspace
For AI engineering teams running regular model evaluations.
Start Free Trial- 1,000 eval credits/month
- 5 team members
- All models & providers
- Blind comparative ranking
- Shareable public reports
- Response caching
- API access & webhooks
- Run comparison & regression
- CSV / JSON export
- Version drift detection
- Pass/fail threshold gates
- BYOK (bring your own keys)
Studio
per workspace
For teams scaling evaluations across models, prompts, and product lines.
Start Free Trial- 4,000 eval credits/month
- 20 team members
- All models & providers
- Blind comparative ranking
- Shareable public reports
- Response caching
- API access & webhooks
- Run comparison & regression
- CSV / JSON export
- Version drift detection
- Pass/fail threshold gates
- BYOK (bring your own keys)
Enterprise
tailored to your org
For organizations that need scale, auditability, and dedicated support.
Contact us- Everything in Studio
- 15,000+ eval credits/month
- Unlimited team members
- Overage billing & volume discounts
- Audit logs
- Dedicated support & SLA
- Custom integrations
All plans include a 14-day free trial with 50 eval credits. No card required to start.
How eval credits work
1 eval credit = 1 generated model response. Evaluator model calls are bundled and free — they never consume credits. Cache hits also consume 0 credits. Formula:
Quick comparison
3 models × 5 topics × 2 personas
30credits
Standard eval suite
5 models × 10 topics × 3 personas
150credits
Full benchmark run
8 models × 20 topics × 4 personas
640credits