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

Playground

Available

Get the prompt right before you write the code.

Compare models side by side, tune parameters, and copy the request as code when the output looks right.

Request accessView pricing
Pricing
Billed as inference
Layer
Inference
Talks to
Catalog models, Managed deployments, Dedicated endpoints, Your fine-tunes

Why Playground

One prompt, several models, one screen.

Send a prompt to any model your workspace can reach, read the answers side by side, and adjust the parameters until the output looks right. Then take the exact request with you as code.

  • Side by side

    Run one prompt against several models at once.

  • Copy as code

    cURL, Python and TypeScript for the exact request.

  • Shared presets

    Save prompts and settings for your team.

How it works

Send a prompt to any model your workspace can reach.

  1. Pick the models

    Choose from catalog models and the deployments your workspace runs, and send one prompt to several of them at once.

  2. Tune the parameters

    Adjust the parameters between runs and compare how each model’s answer changes.

  3. Save a preset

    Keep the prompt and its settings as a preset your team can open and run again.

  4. Copy it, or deploy it

    Copy the exact request as cURL, Python or TypeScript, or deploy the model you settled on as a project of its own.

In the console

Everything in one place.

Playground lives in the LegionEdge cloud console, next to every other service in the workspace, under one account and one identity.

  • Compare

    One prompt against several models, with the answers next to each other.

    • Side-by-side answers for one prompt
    • Any model your workspace can reach
    • Catalog models and your own deployments

  • Presets

    Prompts and settings saved for the whole team.

    • Shared across the workspace
    • Open a preset and run it again

  • Copy as code

    The request you just ran, ready to paste into your project.

    • cURL, Python and TypeScript
    • The exact request, parameters included
    • Points at the same OpenAI-compatible API

  • Deployment playgrounds

    Every model deployment has a playground of its own, for testing before you promote.

    • Calls that deployment’s own URL, not the alias
    • Snippets use the project’s API key
    • Deploy this, straight from the Playground

Pricing

Billed as inference

The Playground carries no charge of its own. Each prompt is billed as the inference it runs on.

  • Serverless models are billed per input and output token.
  • Prompts to a dedicated endpoint run on capacity you already pay for by the GPU-hour.
  • Included on every plan, including Researcher.
Full pricing

Catalog models

Catalog models with context window and token prices
ModelContextInput / 1MOutput / 1M
DeepSeek V4 Flashdeepseek-v4-flash160K$0.30$1.20
DeepSeek V4 Prodeepseek-v4-pro800K$1.74$3.48
Qwen3 0.6Bqwen3-0.6b32K$0.10$0.20
Qwen3 4B Instructqwen3-4b-instruct32K$0.20$0.60
Qwen3.6 27Bqwen3-6-27b256K$0.30$0.90
Qwen3.8 27Bqwen3-8-27b256K$0.30$0.90
GLM-5.2glm-5-2128K$0.50$2.00
GLM-5.3glm-5-31M$0.50$2.00
Kimi K3kimi-k31M$0.60$2.50
Kimi K3 Turbokimi-k3-turbo128K$0.60$2.50

Related products

Pairs well with Playground

Get started

Start with a workload.

Connect to the platform directly, or work with our team on a specific technical challenge.

Self-service

LegionEdge Cloud

Create a workspace, explore the available models, and connect your application. The documentation takes you through your first request.

  • Turn on only the services you need
  • Pay per token or per GPU-hour
  • One account, one bill
Create a workspaceRead the docs

Custom engagements

Work with our team

Bring your data requirements, model goals, or infrastructure constraints. We'll define the scope, deliverables, and next steps together.

  • Scoped with an evaluation baseline
  • Dedicated clusters and reserved GPUs
  • A named engineer from day one
Discuss your projectsales@legionedge.ai