OpenAI-compatible API for accessing multiple AI models with live token pricing
Deploy GPU applications on supported community hardware and cloud capacity
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
SA
Pricing model
Paid
Paid
Pricing
Not given
One published price per GPU model in USD per GPU-hour. Hosts keep 90% of completed rental fees and Petabyte keeps 10%. A reservation holds funds, with final charges and returned balance following settlement after the run completes.
Key features
Live token pricing for 78 models across 11 families
Separate input, output, and cache token rates
Pay-as-you-go and token package billing options
Daily or monthly budget limits per API key
Output and traffic rate limits
Streaming support
Isolated response cache without showing prompt text
Usage records without revealing request content
Choose from available GPU hardware with published hourly rates
Review cost estimates before deployment starts
Start from ready-made template applications
Monitor workload lifecycle states, logs and outputs
Connect your own GPU hardware as a host
Escrow-based payment system for secure transactions
Support for inference model requests
What makes it different
Compare live token prices before sending requests
Single OpenAI-compatible endpoint for multiple model families
Price confirmed before request execution
No silent fallback to pay-as-you-go from packages
Escrow payment ensures work is delivered before host is paid
Transparent pricing: all rates published upfront with no surprises
Minimal transaction fees: hosts keep 90% of rental earnings
Automatic refunds for failed rentals on platform side