Inference.net
Inference.net: Schematron V2 Turbo
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 than through system or user prompts.
Input
$0.03
/ 1M tokens
Output
$0.15
/ 1M tokens
Context window
128K
tokens
Limits
Context
128,000
tokens
Max output
8,192
6.4% of the context window
Model facts
Author
Inference.net
Tokenizer
Other
Modality
Text -> Text
Created
Sep 12, 2026
Hugging Face
inference-net/schematron-v2-granite-4.0-h-micro
Publication status
Hugging Face: unavailableLicense: not publishedParameter count: not published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyLogit biasMax tokensMin pPresence penaltyRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTop kTop p