Why moderate: an exact fingerprint match with one sibling only, and no second signal of a different kind yet.
Inference.net: Schematron V2 Turbo is Inference Net's model. Its measured tokenizer sits with the IBM group, which is evidence that it builds on the IBM tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Inference Net's authorship of the model itself.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 1 other model | tk_b6cc7610 |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_f359f852 |
| How much it can read and write | Reads up to 128,000 tokens at once, writes up to 8,192 | its own listing |
| Who served our requests | InferenceNet | we measured it, 5 October 2026 |
Click a row to open the full comparison.
We sent Inference.net: Schematron V2 Turbo fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
Overhead subtracted: 30 prompt tokens.
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
defaults: {}
