Model dossier

Inference.net: Schematron V2 Turbo

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...

Context128,000
Max output8,192
Pricing viewTVP price

Inference.net: Schematron V2 Turbo

Model ID
inference-net/schematron-v2-turbo
Canonical slug
inference-net/schematron-v2-turbo-20260902
Knowledge cutoff
n/a
Created
9/12/2026
textstructured
text->texttext
Context128,000
Max output8,192
TokenizerOther