The Orchestrator › Models › Inference Net
Inference Net: 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...
Specifications
| Provider | Inference Net |
| Model ID | inference-net/schematron-v2-turbo |
| Context window | 128K tokens (128,000) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, Vercel AI Gateway |
| Released | 2026-09-12 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | inference-net/schematron-v2-turbo | $0.03 | $0.15 | 128K |
| standard | Vercel AI Gateway | inference-net/schematron-v2-turbo | $0.03 | $0.15 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.03 | $0.15 | 128K |
| 2026-11-14 | $0.03 | $0.15 | 128K |
Capabilities
Structured outputs
Supported parameters
frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p