Inference.net pricing

Inference.net API pricing: every model, per million tokens

What Inference.net costs to use and what it costs to build on, each figure carrying the day it was read.

Inference.net

Inference.net API rates

Billed per token and charged separately from any subscription. Read from the provider’s live catalogue every three hours.

Per model, cheapest first

ModelInput / 1MOutput / 1M
Schematron V2 Turbo$0.03$0.15
Schematron V2 Small$0.05$0.23

Questions

How much does the Inference.net API cost?
Inference.net models range from $0.03 per million input tokens (Schematron V2 Turbo) upwards. Every model's input and output rate is listed on this page, confirmed and dated.
How often do Inference.net prices change?
Catalogue prices are re-read every three hours, so a change appears the same day it is published.
WriteWorks

Paying for Inference.net is one cost. Being invisible in it is another.

WriteWorks tracks whether AI answers name your brand or your competitors across 10+ AI platforms, and helps you produce the content that changes the answer.