Inference.net API pricing
As of October 21, 2026, the Inference.net API prices run from $0.15 to $0.23 per million output tokens across 2 models, as listed on OpenRouter. Schematron V2 Turbo is the cheapest paid model at $0.03 input and $0.15 output per million tokens, and Schematron V2 Small the most expensive at $0.05 input and $0.23 output.
None of the 2 models from Inference.net has a benchmark score yet, so none is ranked. No Inference.net model has a published run cost in the sources we read, so cost per solved task shows No run cost rather than an estimate.
| Model | Input $/Mtok | Output $/Mtok | Context | Evidence | Index | Cost per solved task |
|---|---|---|---|---|---|---|
| Schematron V2 Small | $0.05 | $0.23 | 128K | Not benchmarked | No run cost | |
| Schematron V2 Turbo | $0.03 | $0.15 | 128K | Not benchmarked | No run cost |
Price changes
No change in a maker's own API price recorded yet. We read prices daily from OpenRouter (since October 15, 2026) and list a change only when the maker's own price moves between two of our snapshots.