inference-net
2 Inference Net models are available through TokenRoute's OpenAI-compatible API at 30% below Inference Net's own per-token pricing. You call them with the same endpoint and the same API key as every other provider, no separate account, SDK or invoice.
| Model | Context | Input / 1M | Output / 1M |
|---|---|---|---|
| Inference.net: Schematron V2 Small | 128,000 tokens | $0.035 | $0.161 |
| Inference.net: Schematron V2 Turbo | 128,000 tokens | $0.021 | $0.105 |