OPENLLM / COMPUTE SUPPLY

Put your model service to work.

Submit your inference endpoint, model list and pricing for testing and review. Track admission and actual earnings in the supplier console.

01

Prepare your service

Verify the service URL, protocol, dedicated credential, model discovery and a minimal inference request. The endpoint must be reachable by the platform.

02

Submit models and pricing

Provide the compute name, protocol, URL, credential, model list and pricing. The model list and quote accept JSON; see the integration guide for field details.

03

Track testing and review

View submission status, review notes and pricing in My Compute. Submission is followed by testing and review; use the console to check actual availability.

04

Review actual earnings

Review requests, settlement status, platform fees and net earnings. Check supply status when maintaining services or changing models.