Pricing and Deployment
Pricing
Start with a freemium hosted private endpoint, upgrade into dedicated infrastructure, or move to an on-prem platform when customer-controlled deployment and end-to-end encryption requirements increase.
Starter
The easiest entry point for teams that want a private LLM endpoint with OpenAI-compatible API access.
1 hosted private endpoint
1 reveal-once API key
200 requests / day
20 requests / minute
End-to-end encrypted traffic
OpenAI-compatible API
Pro
RecommendedFor teams that want dedicated AI infrastructure and a more isolated deployment boundary.
Dedicated LLM deployment
Private infrastructure boundary
Encrypted private traffic path
Priority support
Deployment guidance
Enterprise
For teams that need a customer-controlled deployment model and on-prem platform rollout.
On-Prem AI Platform
Customer-controlled encryption posture
Architecture review
Custom deployment planning
Implementation support
Deployment ladder
The packaging is intentionally simple. Each plan keeps the product centered on private LLM access, then changes the deployment model as privacy, networking, encryption, and control requirements increase.
Starter
A freemium private LLM endpoint hosted in our infrastructure for fast integration and lower operational overhead.
Pro
Dedicated AI infrastructure for teams that need stronger isolation, more predictable capacity, and tighter operational control.
Enterprise
Run the platform inside your own infrastructure for customer-controlled deployment, internal-only traffic, and stricter security review.
Need a custom rollout?
If you already know the endpoint needs a private network, isolated runtime, or a customer-managed environment, we can scope the correct boundary before rollout.