Schematron V2 Small
by NanoGPT · listed Sep 2026
Inference.net's 3B-parameter HTML-to-JSON extraction model, focused on accuracy for complex schemas and long web pages. It turns HTML into typed, structured data for web scraping and product catalog ingestion, with a 128K-token context window. Supply HTML in the user message and extraction instructions in a JSON schema via response_format; it does not follow ordinary chat or system prompts.
Current rates USD per 1M tokens
Input$0.05
Output$0.23
Cache read$0.025
Cache write—
Against the market
On the record
- Model id
inference-net/schematron-v2-small- Context window
- 128K tokens
- Max output
- 4K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-09-12
- Last updated
- 2026-09-12
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.05 in · $0.23 out
- OpenRouter$0.05 in · $0.23 out
- Vercel AI Gateway$0.05 in · $0.23 out