Inference platform (discounted model router) · LLM APIs
Sells discounted capacity from providers with unused inference headroom — same 'custom, depends on the model' caveat as OpenRouter. Discounts (30-60% off list observed) fluctuate with available supply, so today's rate isn't guaranteed tomorrow's.
Only one tier verified so far — more being added over time.
Want to calculate exact usage instead of just the representative rate? Open the full calculator.