Kaiju Hub AI

Providers

GPU Services — RunPod provider with Setup, Serverless, Cost tabs and Voice/LLM/Image/Video categories

Remote GPU Access via RunPod

RunPod is the active GPU provider. Enable remote GPU access for Voice, LLM, Image, or Video processing. Each category has an independent toggle to enable or disable remote GPU offloading. Uses Public Endpoints (RunPod managed) or Serverless Workers for cloud-based GPU acceleration.

Processing Categories

Voice

Whisper speech-to-text transcription offloaded to remote GPUs for faster processing.

LLM

Large language model inference on remote GPUs.

Image

Text to Image and Image to Image generation. Select models for each generation type.

Video

Text to Video and Image to Video generation. Select models for each generation type.

Available GPU Types

RTX 4090
A100
H100
RTX 3090

API Keys

GPU Services — Setup configuration with Voice, LLM, Image, and Video toggle options

RunPod API Key

Add your RunPod API key to enable remote GPU access. You can generate an API key from your RunPod dashboard. The key is stored locally on your machine and includes a visibility toggle to show or hide the key value.

All third-party logos, trademarks, and brand names displayed in Kaiju Hub AI are the property of their respective owners. Their use is solely for identification purposes and does not imply endorsement, sponsorship, or affiliation.