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...

Details

FieldValue
idinference-net/schematron-v2-turbo
modalitytext->text
context_length128000
max_output_tokens8192
release_date2026-09-12
is_open_weightsno
supports_tool_callno
supports_reasoningno
supports_structured_outputyes
supports_attachmentno
input_modalitiestext
output_modalitiestext