Soft watercolor clouds in lilac, pink and blue

YBacked by Y Combinator

The AI cloud built for
fast-moving startups.

Reserve GPUs, exchange Lilac contracts, or run inference.

View GPU pricing Get started

Trusted by

Why Lilac

Dedicated GPUs. Flexibility built in.

Buy

Capacity from Lilac

Reserve GPU VMs, dedicated nodes, or multi-node clusters from Lilac. We provide the capacity, access, and support.

Resell

Eligible Lilac commitments

Relist an eligible Lilac reservation to another verified Lilac customer. Transfers depend on demand, pricing, and approval.

Monetize

Unused reservation windows

Enable Lilac Flex once and Lilac automatically matches eligible idle windows to approved spot workloads. When demand is matched, the resulting credits reduce your GPU bill.

Products

One GPU Network.
Four ways to use Compute.

Dedicated clusters

Dedicated GPU infrastructure, directly from Lilac

Compare indicative pricing across GPU VMs, bare-metal nodes, and multi-node clusters. Lilac handles capacity, access, and support.

H100 to B300Explore dedicated GPUs

H100H200B200B300

Reserve H100s

Indicative pricing. Final rates depend on configuration and term.

~ $2.00/hr1 month*

~ $1.90/hr6 months*

~ $1.79/hr12+ months*

*Estimate pricing

Serverless

Frontier models, simple per-token pricing

Use supported open models through an OpenAI-compatible API. No GPU reservation, no minimums, and no infrastructure to manage.

4+ modelsExplore models

GLM 5.2

Speed

102 tok/s

Input /M

$0.90

MiniMax M3

TTFT

1.75s

Output /M

$1.10

Gemma 4

Speed

24 tok/s

TTFT

0.46s

Input /M

$0.11

Output /M

$0.35

262KFP8Sub: 75%

Subscriptions

Monthly inference credits that stretch further

Choose a flat monthly credit pool for supported models. Lower-cost capacity lets a predictable subscription cover more product usage.

Up to 12x valueGet started

Basic

$10/mo

$80 value

Pro

$30/mo

$300 value

Max

$100/mo

$1,200 value

Batch

Run GPU jobs to completion

Submit a container image and a command. Lilac runs it on available GPU capacity with simple per-second pricing and no cluster to manage.

Private betaJoin private beta

Batch jobs

Private beta

eval-suite-nightlyrunning

H100 $1.00/hr · 2.82 hrs · ~$2.82

train-baselinerunning

H200 $1.50/hr · 1.14 hrs · ~$1.71

data-processdone

H100 $1.00/hr · 0.46 hrs · ~$0.46

Commitment lifecycle

Commit without getting trapped.

Reserve what you need now. Enable Lilac Flex to automatically monetize eligible idle windows with spot workloads, or transfer an approved Lilac commitment as plans change.

Reserve

Choose the capacity you need now.

Select the GPU, region, scale, and term. The final quote names the site, network, delivery date, and commercial terms.

Lilac Flex

Automatically monetize eligible downtime.

Enable Flex once and Lilac automatically matches eligible idle windows to approved spot workloads. When demand is matched, bill credits lower your effective GPU cost. No manual listings are needed.

Explore Lilac Flex

Transfer

Change the owner when plans change.

Relist an eligible portion of your Lilac commitment to a verified Lilac customer. Lilac qualifies the buyer and coordinates approval.

Explore the exchange

Commitment lifecycle

Commit without getting trapped.

Reserve what you need now. Enable Lilac Flex to automatically monetize eligible idle windows with spot workloads, or transfer an approved Lilac commitment as plans change.

Blog