On-demand GPUs and AI model APIs on one prepaid balance
Stage
Startup
MVP
Founded
2025
Not given
Based in
Not given
Not given
Pricing model
Paid
Paid
Pricing
Starter: 2,150 credits for $9.99 (one-time purchase); XL: 21,500 credits for $99.90 (one-time purchase); Studio: 215,000 credits for $999.90 (one-time purchase); Enterprise: Custom plan available. Model rates vary: Seedance 2.5 starts at $0.1197/s (480p), Seedance 2.0 at $0.0707/s (480p), Seedream 5
GPU rental: $0.15/hr (RTX 2080) to $1.79/hr (H800). Model API calls: Claude Opus 5.5 input $2.00 / output $10.00 per 1M tokens. First top-up of $10 or more earns a $5 bonus.
Key features
REST API with createTask and recordInfo endpoints
Browser-based Studio for creation without coding
Shared credit balance between Studio and API
Published model IDs and rates
Support for video, image, and audio generation
Model comparison and discovery
7 interface languages
OpenAPI documentation
Per-minute GPU billing with no subscription
OpenAI-compatible API endpoint
2-minute GPU deployment
One-click template deployment
Multiple payment methods
Access to Claude, DeepSeek, Qwen, Llama models
No egress charges
Balance never expires
What makes it different
Single unified API for multiple AI providers instead of separate integrations
Same credit balance works in both web Studio and REST API
Published rates and model comparison before choosing
Browser creation for non-developers plus API for automation
Affordable pricing compared to direct provider costs
One balance covers both GPU rental and model API calls
Unused GPU minutes return to your balance when you destroy the instance
Designed for developers worldwide without credit card or phone requirements
Consumer GPU cards like RTX 5090 cost less than US cloud providers
Kinovi
CloudGPU