Best Practices for Building Agents Recap
Arthur

Pricing

Pricing that scales with your AI.

Start free and grow into Premium as you ship more agents. When you need dedicated infrastructure, governance, and support, Enterprise is ready.

Free

$0/mo

Perfect for small teams getting started with AI.

Try for free
  • Monitor model performance with core metrics
  • Cloud data connector integrations built-in
  • Monitoring for up to 4 use cases
  • Unlimited seats for your growing team
Most popular

Premium

$60/mo

For AI-native start-ups and growing orgs.

Request upgrade
  • Everything in Free, plus:
  • Robust capabilities to confidently ship AI agents
  • Customizable performance metrics and dashboards
  • Custom alerting & webhook integrations
  • Monitoring for up to 100 use cases

Enterprise

Custom

For teams with advanced needs or global scale.

Talk to Expert
  • Everything in Premium, plus:
  • Dedicated and managed VPC options to meet your needs
  • Custom data, jobs, traces and evals to fit your needs
  • Dedicated customer success manager
  • Advanced monitoring, SSO, SLAs and BAA

Open source

Arthur Evals Engine

PII, sensitive data, custom LLM, and regex rules built in, with self-serve deployment. For builders and hackers that want to move fast.

Startup Partner Program

Built for venture-backed startups

Venture-backed AI agent startups get Arthur's platform plus hands-on support to ship trustworthy AI faster.

Compare every plan

FreePremiumEnterprise
Governance
Data security
Data locality
SOC 2
Deployment
Multi-tenant SaaS
Single-tenant SaaS
Self-managed VPC / BYOCloud / On-prem
Security & controls
Organizations11Unlimited
Workspaces11Unlimited
Projects210Unlimited
UsersUnlimitedUnlimitedUnlimited
RBAC
API & UI access
SSO
Data
FeaturesUnlimitedUnlimitedUnlimited
Data retention7 days30 daysUnlimited
Cloud data connectors
Custom data connectors
Monitor
Dashboards
Data drift
Performance metrics
Pipeline metrics
Segmentation
Customizable dashboards & metrics
Iterate
Chat playground
Prompt management
Experiment runs
RAG optimization
Evaluate
Datasets
Continuous evals
Custom evals
Tracing
User feedback
Human annotation
Observe
Jobs5k20kCustom
Spans300k1.2MCustom
Inferences12k100kCustom
Evals3k75kCustom
Token & cost tracking
OpenTelemetry
Alerting
Custom alerts3 per modelUnlimitedUnlimited
Alert checks6 per hourUnlimitedUnlimited
Webhooks
Explainability
Explainability methods
"What-If" analysis
Global explanations
Support
Community & email support
Dedicated customer success manager
Dedicated channel
Uptime SLA
Professional servicesAdd-onIncluded

Ready to see Arthur in action?

What Arthur can do for you