Today we're releasing Schematron: 3B and 8B models that extract typed JSON from HTML with frontier-level accuracy. We built Schematron to be the ultimate 𝘸𝘰𝘳𝘬𝘩𝘰𝘳𝘴𝘦 for data extraction: – 50-100x cheaper than GPT-5 – ~10x lower latency – Both models outperform Gemini 2.5 Flash on structured extraction Schematron makes internet-scale structured web data accessible for developers, researchers, and agents. Available now via our serverless API and on HuggingFace. Read the training details and benchmarks on our blog 👇