Skip to main content

​
General FAQ

Runcrate is a unified AI platform that combines three core products:
  • Models API — Access 200+ AI models through a single, OpenAI-compatible endpoint
  • GPU Instances — On-demand GPU-powered Linux environments with SSH access
  • Cloud Storage — Persistent volumes with a built-in file explorer
Everything is managed through a simple dashboard with prepaid credit billing.
Runcrate is designed for:
  • AI developers building applications with LLMs, image generation, or other AI models
  • Researchers who need GPU compute for training, fine-tuning, or experiments
  • Indie hackers who want fast, affordable access to AI infrastructure
  • Teams who need shared projects with role-based access and billing
Over 200 models across 8 categories: Chat, Reasoning, Code, Vision, Image Generation, Video Generation, Text-to-Speech, and Speech-to-Text. This includes models from leading families like GPT-4o, Claude, DeepSeek, Llama, Qwen, Gemini, FLUX, Sora, and more. See the Model Catalog for the full list.
No. The Models API is accessible via HTTP requests from any language or framework. The dashboard is fully web-based. For GPU instances, you only need an SSH client (built into macOS, Linux, and Windows).
There is no free tier. Runcrate uses a prepaid credit system — you add credits and only pay for what you use. You can start with as little as $5.
  • Models API — Instant. Make your first API call as soon as you have a key.
  • GPU Instances — Typically 1 to 3 minutes from deployment to SSH access.