top of page

Choose your pricing plan

  • Free

    0$
     
    The quickest way to experience Plumloom's evaluation approach
    Valid for one week
    • What included:
    • 3 total AI scenario tests (single-run only)
    • Legacy models (GPT-3.5, Claude 2)
    • 7-day data retention
    • 2 test cases per evaluation
    • Basic performance insights
    • Community support
    • Show all features

  • Essentials

    2$
    Every month
    Build confidence in your AI before it meets customers
    Valid for 2 months
    • What included:
    • 100 single-run evaluations/month
    • 300 API call pool for statistical multi-run evaluations
    • Modern models (GPT-4o Mini, Claude 3 Haiku)
    • 30-day data retention
    • 3 test cases per evaluation
    • Advanced performance metrics
    • Show all features

  • Professional

    3$
    Every month
    Scale your AI initiatives while maintaining quality and safety
    Valid for 3 months
    • What included:
    • 400 single-run evaluations/month
    • 1,200 API call pool for statistical multi-run evaluations
    • Modern models (GPT-4o Mini, Claude 3 Haiku)
    • 90-day data retention
    • 5 test cases per evaluation
    • Advanced statistical validation
    • Show all features

  • Unlimited

    4$
    Every month
    Maximize AI performance across your entire organization
    Valid for 4 months
    • What included:
    • Unlimited single-run evaluations
    • 10,000 API calls/month for statistical evaluations (fair use
    • All GPT & Claude models
    • 1-year data retention
    • 10 test cases per evaluation
    • Maximum statistical rigor
    • Show all features

  • Free

    0$
     
    The quickest way to experience Plumloom's evaluation approach
    Valid for one year
    • What included:
    • 3 total AI scenario tests (single-run only)
    • Legacy models (GPT-3.5, Claude 2)
    • 7-day data retention
    • 2 test cases per evaluation
    • Basic performance insights
    • Community support
    • Not included
    • Single-run only - results may vary
    • 100 single-run evaluations/month
    • Modern models access
    • 30-day data retention
    • Email support
    • Multi-run statistical validation
    • Show less

  • Essentials

    288.12$
    Every year
    Build confidence in your AI before it meets customers
    Valid for 2 years
    • What included:
    • 100 single-run evaluations/month
    • 300 API call pool for statistical multi-run evaluations
    • Modern models (GPT-4o Mini, Claude 3 Haiku)
    • 30-day data retention
    • 3 test cases per evaluation
    • Advanced performance metrics
    • Email support
    • 500 daily API call safety limit
    • $0.35 per evaluation after pool exhausted
    • Not included
    • 400 single-run evaluations/month
    • 1,200 API call pool
    • 90-day data retention
    • Priority support
    • Safety & bias protection
    • Show less

  • Professional

    887.64$
     
    Scale your AI initiatives while maintaining quality and safety
    Valid for one year
    • What included:
    • 400 single-run evaluations/month
    • 1,200 API call pool for statistical multi-run evaluations
    • Modern models (GPT-4o Mini, Claude 3 Haiku)
    • 90-day data retention
    • 5 test cases per evaluation
    • Advanced statistical validation
    • Safety & bias protection
    • Professional analytics dashboard
    • Priority support
    • Export evaluation reports
    • 1,000 daily API call safety limit
    • $0.25 per evaluation after pool exhausted
    • Not included
    • Unlimited single-run evaluations
    • All GPT & Claude models
    • 1-year data retention
    • Show less

  • Unlimited

    1,980.84$
    Every year
    Maximize AI performance across your entire organization
    Valid for 2 years
    • What included:
    • Unlimited single-run evaluations
    • 10,000 API calls/month for statistical evaluations (fair use
    • All GPT & Claude models
    • 1-year data retention
    • 10 test cases per evaluation
    • Maximum statistical rigor
    • Advanced safety & compliance
    • Phone support
    • 2,000 daily API call safety limit
    • Enterprise discussion for usage above fair use
    • Show less

  • Free 1

    2$
    Every month
    Valid for 2 months
    • 3 total (lifetime)
    • N/A
    • Legacy
    • 1
    • 2
    • Single-run only - results may vary
    • Core reliability insights
    • Community
    • 7

  • Essential 1

    0$
     
    Valid for one month
    • 100 single-run/month + 300 API call pool
    • 500 API calls
    • Modern
    • 3
    • 5
    • Multi-run statistical validation with smart convergence
    • Comprehensive performance analysis with confidence intervals
    • Essential evaluation tracking
    • Email
    • 30 days
    • $0.35 per evaluation after API pool exhausted

  • Professional 1

    0$
     
    Valid for one month
    • 400 single-run/month + 1,200 API call pool
    • 1,000 API calls
    • Modern
    • 10
    • 5
    • Multi-run statistical validation with smart convergence
    • Comprehensive performance analysis with confidence intervals
    • Strategic insights for AI optimization
    • Priority
    • 90 days
    • $0.25 per evaluation after API pool exhausted

  • Unlimited 1

    0$
     
    Valid for one month
    • Unlimited single-run + 10,000 API calls/month
    • 2,000 API calls
    • All models
    • 25
    • 10
    • Multi-run statistical validation with smart convergence
    • Comprehensive performance analysis with confidence intervals
    • Strategic insights for AI optimization
    • Phone
    • 1 year
    • Enterprise discussion for usage above fair use
bottom of page