Inference.netFastFastActive
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...
Specification
- Model ID
- inference-net/schematron-v2-turbo
- Modality
- Text >text
- Context
- 128K tokens
- Input
- $0.030/1M
- Output
- $0.150/1M
- Updated
- Sep 20, 2026
Scores
Capabilities
- No tool calling listed
- No vision support listed
- Supports long-context workflows
- Lighter reasoning profile
Input and output
Accepts Text inputs. Returns Text outputs.
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p