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. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.
inference-net/schematron-v2-turbo
- Context
- 128k tokens
- Completion cap
- 8,192
- Tools
- No
- JSON
- Yes
- Released
- 2026-09-12
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "inference-net/schematron-v2-turbo",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is 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. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts. Schematron V2 Turbo runs on the Geek Hub API (OpenAI-compatible). Model id: inference-net/schematron-v2-turbo.
- Is Schematron V2 Turbo free?
- No. Input is $0.0327 per 1M tokens and output is $0.1635 per 1M tokens on Geek Hub (markup included).
- What is the context length of Schematron V2 Turbo?
- Schematron V2 Turbo has a 128k tokens context window. It supports up to 8,192 completion tokens.
- Does Schematron V2 Turbo support tool calling and structured outputs?
- Schematron V2 Turbo does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
- When was Schematron V2 Turbo released?
- Schematron V2 Turbo was released on 2026-09-12.