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
| Model | Input | Output | Accepts |
|---|---|---|---|
| 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.
02Makers
Other makers.
The makers with the most models in the catalog besides Inference.net.
Put Inference.net’s models to work.
Every model on this page opens in the same chat.