Starter
Build
For small teams validating models and pipelines.
$49/mo
- Up to 1M requests/month
- 2 production environments
- Community + async support
- Basic observability dashboards
Pricing
Predictable pricing for every stage of scale.
Start free, move to growth, then unlock enterprise architecture. No hidden fees. Clear usage economics and consistent support at every tier.
Growth
Scale
For shipping teams with production traffic and SLAs.
$199/mo
- Up to 20M requests/month
- Priority autoscaling lanes
- Advanced security controls
- Slack + 24h support SLA
Enterprise
Operate
For regulated teams requiring custom architecture and controls.
Custom
- Private networking + tenancy
- Custom compliance workflows
- Dedicated TAM + architecture lead
- 99.99% contractual SLA
Included in every plan
Reliability and governance are baseline.
Every tier includes encrypted transport, structured logs, policy controls, and deployment history. As your traffic grows, controls deepen instead of fragmenting.
Model VersioningIncluded
RBAC + Access PoliciesIncluded
Token + Cost AnalyticsIncluded
Audit TrailsIncluded
Webhook AutomationsIncluded
FAQ
Pricing questions teams ask first.
How does usage-based billing work?
Usage is metered by requests, compute seconds, and storage. You get clear unit-based reporting with thresholds and alerts before overages happen.
Can we move between plans without downtime?
Yes. Plan upgrades and downgrades are immediate at billing boundaries and do not interrupt active model deployments.
Do annual plans include support benefits?
Annual plans include discounted rates and expanded support windows. Enterprise agreements include named technical contacts and onboarding workshops.