Schematron V2 Small
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages.
The figures
- Made by
- Inference.net
- Model ID
- inference-net/schematron-v2-small
- Input
- $0.05 per million tokens
- Output
- $0.23 per million tokens
- Context window
- 128K tokens
- Longest answer
- 4K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- No
- Tool calling
- No
- Reads images
- No
- Open weights
- Yes
- Released
- 12 Sept 2026
Read on 3 Oct 2026.