Schematron V2 Small
inference-net/schematron-v2-smallSchematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages.
$0.050Input, per million tokens
$0.23Output, per million tokens
128KContext window
4KLongest answer
128K tokens of context — about 96,000 words, on a scale that ends at 2M.
What it can do
- Open weights
- Takes text
- Gives text
Released 12 Sept 2026 · checked 3 Oct 2026.