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
| Field | Value |
|---|---|
| id | inference-net/schematron-v2-turbo |
| modality | text->text |
| context_length | 128000 |
| max_output_tokens | 8192 |
| release_date | 2026-09-12 |
| is_open_weights | no |
| supports_tool_call | no |
| supports_reasoning | no |
| supports_structured_output | yes |
| supports_attachment | no |
| input_modalities | text |
| output_modalities | text |