Skip to content
Sign inRequest access

Products

GPU CloudAMD MI325X and NVIDIA H200 by the hour or on reservation.
Dedicated ClustersPreviewPrivate, interconnected GPU clusters for sustained workloads.
SandboxesPreviewIsolated, short-lived environments for developers and AI agents.
Serverless GPUPreviewGPU containers that scale with requests, down to zero.
Serverless InferenceOpen models behind one OpenAI-compatible endpoint.
Dedicated EndpointsReserved serving capacity for one model, billed per GPU-hour.
PlaygroundSend a prompt to any model your workspace can reach.
Model DeploymentsPreviewImmutable deployments with instant promote and rollback.
Fine-tuningLoRA fine-tunes on the open models in our catalog.
Model TrainingPreviewFoundation-model training runs, managed end to end.
EvaluationsPreviewBenchmark suites and model comparisons you can rerun.
DatasetsManaged and synthetic training data, versioned and ready to use.
Data ManagementPreviewDatasets, connections and storage, with lineage across the platform.
PipelinesPreviewVersioned DAGs that automate data, training and deployment.
Data RoomsPreviewSecure document sharing with guests, NDAs and an audit trail.
NokuvaPreviewThe AI-native design editor.
TavocPreviewA Rust-native code platform: IDE and desktop apps.
FoltracComing soonMulti-cloud deployment with autonomous operations.
W0rkTreeComing soonVersion control for agent fleets.
Identity & AccessMembers, roles, policies, SSO and audit for every workspace.
Billing & CostUsage, invoices, credits and budgets in one place.
Logs & MonitoringRequest logs, latency and error rates across services.
Project CanvasPreviewSee and change a project's resources on one live canvas.

Pages

Home/
Platform/platform
All products/products
Pricing/pricing
GPU pricing/pricing#compute
Inference services/services/inference
Model training services/services/model-training
Protocol design/services/protocol-design
Research partnerships/services/research-partnerships
Protocols/protocols
Datasets/datasets
Documentationdocs.legionedge.ai
Changelog/changelog
News/news
Research/research
Blog/blog
Articles/articles
Events/events
Startup Program/programs/startup
Ambassador Program/programs/ambassador
Partner Program/programs/partner
Event Program/programs/events
Company/company
Careers/careers
Partners/partners
Contact/contact
Statusstatus.legionedge.ai
Terms of Service/legal/terms
Privacy Policy/legal/privacy

LegionEdgeandGoogle Cloud

Preview

Google Cloud GPUs, in the LegionEdge console.

Launch Compute Engine GPU VMs, GKE node pools and Cloud Run GPU services from the same console, canvas and API as the rest of your workspace. Google Cloud shows up as a provider badge on an offer; you never need its console.

Request accessView pricing

On Google Cloud

  • Compute Engine
  • Google Kubernetes Engine
  • Cloud Run
  • Vertex AI
  • Cloud Marketplace

What you get

Google Cloud, without leaving LegionEdge.

Each one is a service in your workspace, under the same identity, permissions, audit log and bill as everything else.

  • GPU VMs

    Compute Engine A3 with H100 or H200, A4 with B200 and G2 with L4, on demand or spot. Start, stop, reinstall and delete from the console, with serial logs and GPU metrics alongside.

    GPU Cloud

  • GKE GPU clusters

    GKE clusters with GPU node pools and drivers installed, registered as capacity for your workloads and staged on the canvas like any other cluster.

    Dedicated Clusters

  • Cloud Run GPU

    Deploy a container with an NVIDIA L4 or RTX PRO GPU and get a URL. Services scale between the limits you set and down to zero, billed by the second they run.

    Serverless GPU
  • Your own Google Cloud project only

    Vertex AI endpoints

    Serve a dedicated model deployment on a Vertex AI endpoint behind your LegionEdge URL, with the same routing, keys and logs as every other deployment.

    Model Deployments

  • Cloud Marketplace

    Buy LegionEdge through Google Cloud Marketplace and settle it on your Google Cloud bill. A Marketplace sign-up becomes an access request, and our approval still applies.

The partnership

LegionEdge partners with Google Cloud

PartnershipRead the announcement

LegionEdge and Google Cloud are entering a formal partnership. A dedicated cluster of NVIDIA H200 Tensor Core GPUs is now online on Google Cloud, reserved for model training, dataset generation, and the open research that lands in our registry.

The partnership runs in both directions: Google Cloud carries our heaviest workloads, and Google Cloud becomes a first-class target across everything we ship — Foltrac deploys to it natively, and LegionEdge Cloud schedules training and inference on it, including capacity you bring yourself.

How it works

GPU VMs, GKE, Cloud Run GPU and Vertex AI through one console and one bill.

  1. Connect

    Managed capacity is ready in every workspace. To use your own project, run the generated gcloud script or Terraform snippet: it creates a workload identity pool and a least-privilege service account.

  2. Pick an offer

    Choose by GPU, region, price and availability. Offers follow your project's quotas, so what you see is what you can launch.

  3. Launch or stage

    Launch from the wizard, or stage the instance on the canvas and apply it with the rest of a changeset.

  4. One bill

    Usage is metered by LegionEdge and lands on the same statement, budgets and cost explorer as everything else, tagged with the provider.

Accounts

Ours, or your own.

Run on LegionEdge's Google Cloud account, or connect the one you already have. Credentials stay on the server as workspace secrets and never reach the browser.

  • Managed by LegionEdge

    Capacity in LegionEdge's own Google Cloud organization, on shared pools. Pay for what you run at LegionEdge rates.

    • Nothing to set up
    • One network per organization, a subnet per region
    • Billed on LegionEdge meters

  • Your own project

    Connect a Google Cloud project you already have, with its own quotas and network. The connection is visible only inside your organization.

    • Workload Identity Federation, no stored keys
    • Your quotas drive what you can launch
    • Compute stays on your Google Cloud bill

Pricing

Billed on LegionEdge meters.

Managed capacity is billed per GPU-hour and per second of Cloud Run GPU time, on the same statement as the rest of your workspace. Your own project's compute stays on your Google Cloud bill.

  • Spot capacity is billed on its own, lower meter
  • Budgets can stop new launches or drain running ones
  • Customers are charged on LegionEdge meters, never a passed-through Google Cloud invoice
Full pricing
Google Cloud usage meters and their list prices
ResourcePrice
NVIDIA H100per GPU-hourNot yet published
NVIDIA H200per GPU-hourNot yet published
NVIDIA B200per GPU-hourNot yet published
NVIDIA L4per GPU-hourNot yet published
Cloud Run GPU, NVIDIA L4per GPU-secondNot yet published
Cloud Run vCPUper vCPU-secondNot yet published
Platform fee, your own projectper instance-hourNot yet published

Google Cloud rates appear here once they are published in the LegionEdge price book. Until then, ask our team for a quote.

Partner Program

Ready to build with us?

The Partner Program covers every track — certification, co-selling, escalation, and the application form to get started.

Explore the Partner ProgramTalk to partnerships