Schematron V2 Turbo

How this price is scoped: Inference.net makes this model and is its only seller, so this is a first-party list price. Its own model catalogue at inference.net/models (read 2026-09-16, receipt data/evidence/inference-net-schematron-v2-turbo/2026-09-16.txt) prints the row "Schematron V2 Turbo / INFERENCE.NET / 125K input context / $0.03 / $0.03 / $0.15 / inference-net/schematron-v2-turbo" — the three money cells are input, cache read and output in that column order — and the model's own page at inference.net/models/schematron-v2-turbo prints the same three figures under "Model API pricing — Per 1M tokens". The catalogue's embedded record states them per token — costInputPerToken 0.000000030000, costCachedInputPerToken 0.000000030000, costOutputPerToken 0.000000150000 — which is $0.03 / $0.03 / $0.15 per 1M. OpenRouter's endpoint list for inference-net/schematron-v2-turbo (read 2026-09-16) returns exactly ONE endpoint, provider_name "InferenceNet", at prompt 0.00000003 / completion 0.00000015 / input_cache_read 0.00000003 and discount 0, so the maker's own figure and the only routed figure agree to the cent. No promotional or introductory marker appears against either SKU on the catalogue.