# Inference.net: Schematron V2 Turbo

Provider: inference-net  
Category: llm  
Model ID: `inference-net/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...

## Specs

- Context length: 128000 tokens
- Max output: 8192 tokens
- Modalities: text
- Released: 2026-09-12

## Pricing

- Input: $0.03 per million tokens
- Output: $0.15 per million tokens

## Providers

- **inference-net** — ctx 128000, input $0.03/M, output $0.15/M

## Verdict

Schematron V2 Turbo targets cost-conscious teams needing a large context window without premium pricing. At $0.03/$0.15 per Mtok, it undercuts most 128K-context competitors by 40-60%. The trade-off: no public benchmarks mean you're flying blind on reasoning quality, code accuracy, and instruction-following relative to known models. Reach for this when budget constraints matter more than proven performance, or when you're willing to validate outputs carefully in exchange for lower inference costs.

---
Last verified: 2026-10-19T02:30:34.239Z  
Canonical URL: https://switchy.build/directory/models/schematron-v2-turbo