inference-net API Pricing
All 2 inference-net models by input price. Refreshed hourly.
FAQ
What is the cheapest inference-net model?
By input price, Inference.net: Schematron V2 Small is lowest ($0.05/1M tokens). See the full table above.
How is inference-net priced?
Usage-based: input and output priced separately per 1M tokens, with cache read/write discounts on some models. The Blended column estimates a typical 3:1 request cost.