Skip to content

Inference.net models

Upend lists 2 Inference.net models. The newest is Schematron V2 Turbo, added to the catalog on 12 Sep 2026. Input prices run from $0.03 to $0.05 per 1M tokens. The largest context window is 128K tokens (Schematron V2 Turbo).

Last checked · source: OpenRouter

2 models by Inference.net · newest first

Inference.net models, newest first, with context window and price per 1M tokens
Model Input Output
Schematron V2 Turboinference-net/schematron-v2-turbo $0.03 $0.15
Schematron V2 Smallinference-net/schematron-v2-small $0.05 $0.23

Prices are list prices through OpenRouter. A variant of a model (free, batch, extended) is a column on that model's page, not a row here.

Inference.net models compared

Each model side by side with the next one up in Inference.net's line-up.

Put Inference.net’s models to work.

Every model on this page opens in the same chat.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.