Back to all models
inference-net
inference-netInference.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...
inference-net/schematron-v2-turbo
Context Size
128K
Input Price
4,500 pts/M277 Ks/M
Output Price
22,500 pts/M1,384 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
Details
TokenizerOther
Max Completion8,192 tokens
Provider Context128K tokens
ModeratedNo
CreatedSep 12, 2026