Deployments
Model Guides
Select, configure, and access models through the InferX Console.
Published endpoints
Published endpoint pages expose model metadata and identifiers. Sign in when you are ready to copy the tenant-scoped URL, API key, and runnable integration flow.
Dedicated model deployment
The existing Console supports Deploy From Catalog and Build From Scratch. The configuration flow includes the model identifier, vLLM image, runtime parameters, GPU count, and vRAM.
Gated model access
For gated Hugging Face models, accept the model license and provide HF_TOKEN through the Console’s advanced environment configuration.