← all releases
Inference.net·Aug 20, 2025·v1.0·open source
Schematron-3B
Schematron-3B is a long-context extraction model designed to convert noisy HTML into clean, typed JSON that adheres to a user-provided schema. It is specifically trained for web scraping, data ingestion, and transforming arbitrary web pages into structured records.
Infrastructure
overview
Schematron-3B is a long-context extraction model designed to convert noisy HTML into clean, typed JSON that adheres to a user-provided schema. It is specifically trained for web scraping, data ingestion, and transforming arbitrary web pages into structured records.
key features
- 01Schema-first extraction: Outputs strictly conforming JSON to the provided schema
- 02Long context: Handles lengthy, noisy HTML up to 128K tokens
- 03Variants: Available in 3B (default, cost-efficient) and 8B (higher quality) sizes
related productsbrowse all →
Planoopen sourcePlano is an AI-native proxy and data plane designed to streamline the development of agentic applications. By offloading the underlying infrastructure tasks, it allows developers to focus on the core logic of their agents, regardless of the AI framework in use.QueryWeaveropen sourceQueryWeaver is an open-source Text2SQL tool developed by FalkorDB that transforms natural language queries into SQL using graph-powered schema understanding. It enables users to interact with databases in plain English, simplifying the process of generating accurate SQL queries. ([github.com](https://github.com/FalkorDB/QueryWeaver?utm_source=openai))AIO Sandboxopen sourceAIO Sandbox is an integrated environment designed for AI agents, combining a browser, terminal, filesystem, VSCode, Jupyter, and MCP Server into a single Docker container. This unified setup allows seamless development and execution of AI agents without the need for multiple services.