Loading the SOTA2 catalog…
Lilac
Lilac is the GPU cloud built for fast-moving startups, with dedicated NVIDIA GPU infrastructure, OpenAI-compatible serverless inference, and flexible options for committed capacity.
- Founded
- 2025
- Headquarters
- San Francisco
- Company size
- 1–10
- Products tracked
- 6
Products by Lilac
Pricing for Lilac
Usage Based, Subscription, Per Seat
This is the broad commercial model reported for Lilac. Product-level terms are listed below when available.
- Pricing model
- Usage Based
- Starting price
- ~$1.79/hr (12+ month commitment, H100)
- Pricing model
- Usage Based
- Starting price
- $0.05/M tokens (MiniMax M3 cache read)
- Pricing model
- Subscription
- Starting price
- $10/mo (Basic tier, up to $80 value)
- Pricing model
- Usage Based
- Starting price
- H100 $1.00/hr (per-second billing)
- Pricing model
- Usage Based
- Pricing model
- Usage Based
Trust profile
Security and compliance
SOC 2
API inputs and outputs are not stored at rest; exist only in memory during inference and deleted immediately afterward
No training on API inputs or outputs
No sharing of API data with third parties
No logging of prompts or completions; only metadata (request ID, token counts, sampling parameters) is logged for billing and debugging
Technical, organizational, and physical safeguards to protect information