Schematron V2 Turbo
Schematron V2 Turbo is a 3B-parameter model developed by Inference.net designed specifically for extracting data from HTML into JSON format. It is optimized for high-throughput environments where large volumes of web data need to be structured efficiently.
Schematron V2 Turbo specs and pricing
- Provider: Inference.net
- Released: September 12, 2026
- Context window: 128K tokens
- Max output: 8K tokens
- Input: text
- Output: text
- Price: $0.03 input / $0.15 output per 1M tokens
What Schematron V2 Turbo is good at
- Converting large-scale HTML web content into structured JSON
- High-volume data extraction pipelines
- Automated parsing of web-based information
To-dos to try with Schematron V2 Turbo
- Extract all product prices and availability statuses from this HTML snippet into a JSON object.
- Parse the provided HTML table of contents into a structured JSON hierarchy.
- Convert this raw HTML article into a JSON format with fields for the title, author, and body text.
FAQ
- What is the primary function of Schematron V2 Turbo? It is a specialized model built to extract information from HTML and output it as structured JSON.
- Can this model process images or other media files? No, the model only supports text as both input and output.
- How much does Schematron V2 Turbo cost? Schematron V2 Turbo costs $0.03 per million input tokens and $0.15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.11 credits ($1 = 100 credits).
- What is the context window of Schematron V2 Turbo? Schematron V2 Turbo can read up to 128K tokens at once and write up to 8K tokens in one reply.
- Can I use Schematron V2 Turbo without coding? Yes. In todo.is you pick Schematron V2 Turbo as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.