Schematron V2 Turbo
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads.
The figures
- Made by
- Inference.net
- Model ID
- inference-net/schematron-v2-turbo
- Input
- $0.03 per million tokens
- Output
- $0.15 per million tokens
- Context window
- 128K tokens
- Longest answer
- 8K 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.