CONTROL CENTER
Overview.
Your model infrastructure, at a glance.
YOUR AI, YOUR INFRASTRUCTUREOne model.
One model.
Every workflow.
Deploy qwen3:8b on FluxEdge and connect it to the tools you already use.
Account
Balance—
Spend / hr—
Deployment
none
No deployment yet.
INFRASTRUCTURE
Deploy.
Put qwen3:8b to work on your own GPU instance.
Current deployment
none
No deployment yet.
FluxEdge deployment
Direct API base URL
Router API base URL
Use your LiteLLM master key for the direct API, or a key from the API Keys page for the router API.
Configuration
Set the limits for your next GPU rental.
ⓘ Deploying rents real hardware and starts billing immediately. This can take 1–3 minutes.
ACCESS MANAGEMENT
API Keys.
Give your tools secure access to the model.
Your API keys
| Name | Token | Created |
|---|
Copy this now — it won't be shown again.
ConversationInteractive model session
✳
READY WHEN YOU AREStart a conversationSend a message to test your deployed model.
Your conversation stays in this session.
INTEGRATIONS
Connect.
Bring the model into your favorite tools.
Base URL
Point your harness at wherever this portal is reachable, with /v1 appended
(e.g. <this-server>/v1). Use a key from the API Keys page.