Home › Providers › inference-net
inference-net API Pricing
inference-net offers 2 API models in the catalog. Combined input+output prices range from $0.18 (Inference.net: Schematron V2 Turbo) to $0.28 (Inference.net: Schematron V2 Small) per 1M tokens. Its most recent model is Inference.net: Schematron V2 Turbo at $0.03 input / $0.15 output.
| Model | Input /1M | Output /1M | Cached in /1M | Context |
|---|---|---|---|---|
| Inference.net: Schematron V2 Turbo | $0.03 | $0.15 | $0.03 | 128,000 |
| Inference.net: Schematron V2 Small | $0.05 | $0.23 | $0.05 | 128,000 |
Frequently asked questions
What is the cheapest inference-net model?
The cheapest inference-net model by combined price is Inference.net: Schematron V2 Turbo at $0.03 input and $0.15 output per 1M tokens.
How many models does inference-net offer via API?
inference-net lists 2 models in the OpenRouter catalog as of October 21, 2026.
Price snapshot October 21, 2026, refreshed daily.