Simple, transparent pricing
Scale from prototype to production with explicit limits and no surprises. Every tier includes the same core framework.
Free
Best effort shared pool for prototyping
Perfect for getting started
- ✓ Shared LLM pool (best effort)
- ✓ 10 remote tool executions/day
- ✓ 5 published tools
- ✓ 2k metrics & 1k spans/day
- ✓ 7-day data retention
- ✓ Community support
Explorer
For individual developers and small teams
Great for small teams and side projects
- ✓ 30 guaranteed LLM messages/day
- ✓ 500 remote executions/day
- ✓ 25 published tools
- ✓ 50k metrics & 20k spans/day
- ✓ 30-day data retention
- ✓ Email support
Team
For growing teams with production workloads
Built for production teams
- ✓ 300 guaranteed LLM messages/day
- ✓ 10k remote executions/day
- ✓ 100 published tools
- ✓ 500k metrics & 200k spans/day
- ✓ 90-day data retention
- ✓ Priority support
Enterprise
On-premises or private cloud deployment
Unlimited scale in your infrastructure
- ✓ Unlimited throughput
- ✓ Deploy in your VPC/on-prem
- ✓ No enforced limits
- ✓ Self-managed pipeline
- ✓ Custom retention policies
- ✓ Dedicated support & SLA
Service Limits & Quotas
Detailed breakdown of limits by service and tier. All limits are enforced transparently with clear time units.
All Services
Complete breakdown of what each tier includes
| Service | Metric (per time unit) | Free | Explorer ($50/mo) | Team ($500/mo) | Enterprise (On-Prem / Private Cloud) |
|---|---|---|---|---|---|
| LLM API | Guaranteed user messages / day | Shared pool – best effort | Up to 30 msgs / day | Up to 300 msgs / day | Unlimited – throughput defined by infra |
| Tool Registry & Remote Tools | Remote executions / day · Published tools (total) | 10 exec / day · 5 tools total | 500 exec / day · 25 tools total | 10k exec / day · 100 tools total | No enforced limits; deploy in-VPC |
| Observability Ingestion | Metrics + spans / day · Retention (days) | 2k metrics / day 1k spans / day · 7-day retention | 50k / 20k · 30 days | 500k / 200k · 90 days | Self-managed pipeline · retention by ops |
| Audit Logging | Events / day · Retention (days) | 2k / day · 7 days | 20k / day · 90 days | 250k / day · 365 days | Unlimited events · export/API streaming |
| Managed Conversation Store | Active conversations (total) · Storage (GB) · Retention (days) | 100 conv 1 GB · 7 days | 1k 10 GB · 90 days | 10k 200 GB · 365 days | Bring-your-own storage · configurable residency |
| Agent Memory | Memory writes / day · Vector storage (total GB) | 500 writes / day · 100 MB total | 5k writes / day · 2 GB total | 100k writes / day · 50 GB total | Unlimited writes · private VPC peering |
Understanding Time Units
Our pricing uses three different types of resource limits. Here's what each means:
Frequently Asked Questions
What happens if I exceed my daily limits?
Daily throughput limits reset every 24 hours. If you exceed your limit, requests will be rate-limited until the next reset. You can upgrade to a higher tier at any time for immediate access to higher limits.
Can I start with the open source version and upgrade later?
Yes! All tiers use the same core framework. You can start self-hosting with the open source version, then seamlessly upgrade to our managed cloud platform or enterprise deployment without rewriting your code.
What's included in the free tier?
The free tier gives you access to all services with reduced quotas and best-effort LLM access. It's perfect for prototyping and learning. You get 10 tool executions per day, 5 published tools, basic observability, and 7-day data retention.
How does Enterprise pricing work?
Enterprise pricing is custom based on your deployment needs (on-prem, VPC, or private cloud), desired SLAs, and support requirements. Contact our sales team to discuss your specific requirements.
Do you offer annual discounts?
Yes! Annual subscriptions receive a 20% discount. Contact sales or select annual billing during checkout.
Ready to get started?
Start with our free tier today. No credit card required. Upgrade anytime as your needs grow.