Pay for the answer, not the tokens
Every model tested on your workflows, inference at list price
Pro
$50/ monthFor one builder with a few workflows
Credits each month1,000
- 3 tracked workflows
- Unlimited runs, models, and test cases
- Buy credits or auto top-up
- Reruns on every release
- Shareable reports
- Your own API keys, no markup
TeamMost teams
$200/ monthFor product teams choosing models every week
Credits each month6,0005,000 + 1,000 bonus
- 15 tracked workflows
- Unlimited runs, models, and test cases
- Buy credits or auto top-up
- Everything in Pro
- Rubric and custom judges
- Slack and email on every release
Enterprise
CustomFor larger teams with security and procurement needs
Credits each monthVolume-scaled
- Unlimited tracked workflows
- Unlimited runs, models, and test cases
- Usage-based overage billing
- SSO and audit log
- Data retention you set
- Custom terms and support
Expert help
An expert designs your evals, picks your models, and keeps them current
Compare plans | Pro$50 / month | Team$200 / month | EnterpriseCustom |
|---|---|---|---|
| Evals and judges | |||
| Tracked workflows | 3 | 15 | Unlimited |
| Credits each month | 1,000 | 6,000 | Volume-scaled |
| Runs, models, and test cases | Unlimited | Unlimited | Unlimited |
| Exact-match judges | |||
| Rubric judges | — | ||
| Your own scoring script | — | ||
| Models and reruns | |||
| Every frontier model | |||
| Rerun on every release | |||
| Your own API keys, no markup | |||
| Trusted-access cyber models | — | — | Klu for Security |
| Credits and billing | |||
| Extra credits | Packs or auto top-up | Packs or auto top-up | Agreed rates |
| Annual contract | — | — | |
| Reports and alerts | |||
| Shareable reports | |||
| Email on every release | |||
| Slack alerts | — | ||
| Team | |||
| Seats | 1 | 10 | Unlimited |
| Workspace roles | — | ||
| Security | |||
| AES-256-GCM encryption | |||
| SSO | — | — | |
| Audit log | — | — | |
| Data retention controls | — | — | |
| Private cloud | — | — | Add-on |
| Support | |||
| Email support | |||
| Dedicated success team | — | — | |
| Advisory | — | Add-on | Add-on |
| Start with Pro | Start with Team | Talk to us |
Estimate your monthly bill
Tracked workflowsWorkflows you rerun on every release
Cases per evalGraded answers in each rerun
Releases a monthFrontier releases you rerun on
KluTeam plan$200/ month
Billed by Klu. Credits cover grading, reruns, and reports≈ 4,960 credits used6,000 included
LabsInferenceBilled by the labs on your API keys, at list price
Questions
- What is a credit?
- Credits pay for the work Klu runs for you, which is building benchmarks, grading answers, and simulating users. A benchmark build takes 12 credits per case, and grading 100 answers takes about 124.
- What happens when I run out?
- New runs wait until you add credits. With auto top-up on, Klu buys the pack you picked whenever your balance drops below the level you set.
- Can I go over my credits?
- Yes. Credit packs are 600 for $10, 2,000 for $30, and 3,500 for $50, and auto top-up can buy them for you. Enterprise plans use the overage rates in your agreement.
- Who bills inference?
- The model providers, on your own API keys at their list price. Klu never marks it up.
- Can I change or cancel?
- Anytime. Plans are month to month, and changes take effect at your next renewal.
- Do you offer annual plans?
- Annual contracts are available on Enterprise. Pro and Team are monthly.
Start with one workflow
Describe what you built and see your first report before the next model ships