Schematron V2 Small
Schematron V2 Small is a large language model made by Inference.net, added to the catalog on 12 Sep 2026. It has a context window of 128,000 tokens and costs $0.05 per 1M input tokens and $0.23 per 1M output tokens. It accepts text and produces text. Typical uses: extracting structured records from HTML pages, processing lengthy page content and extracting information using complex JSON schemas.
Price checked ยท source: OpenRouter
What Schematron V2 Small is
Schematron V2 Small is an HTML-to-JSON extraction model from Inference.net. It accepts text and produces text, with extraction instructions supplied through a JSON schema. The schema defines the requested output format, orienting the model toward converting page content into structured text rather than producing general prose. Its stated focus is extraction quality for complex schemas and long pages.
The model has a context length of 128,000 tokens and a maximum output of 8,192 tokens. Its context can hold page content and schema instructions in the same request, while the output limit sets the maximum size of a generated response. Schematron V2 Small supports structured outputs and a response-format setting. These features suit workflows that specify the structure expected from an extraction request. The catalog does not name particular fields or schema formats beyond JSON schema.
The model is intended for text-based extraction; the catalog lists text as its input and output and does not specify other input modalities. It may suit turning HTML page content into structured records, extracting information from lengthy pages, or working with detailed schemas. The catalog does not identify specific industries, data domains, or integrations, so its fit depends on whether a task can be expressed using text and JSON schema instructions.
Key features
- Converts HTML page content into JSON through schema-based extraction instructions
- Accepts text and produces text
- Has a context length of 128,000 tokens
- Supports structured outputs and response-format settings
- Has a maximum output of 8,192 tokens
Typical uses
- Extracting structured records from HTML pages
- Processing lengthy page content
- Extracting information using complex JSON schemas
- Converting page text into schema-defined output
Schematron V2 Small pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.05 |
| Output, per 1M tokens | $0.23 |
| Cached input read, per 1M tokens | $0.05 |
No price change since it was added on 12 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0014 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0020 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0078 |
Schematron V2 Small specifications
| Model id | inference-net/schematron-v2-small |
|---|---|
| Version | schematron-v2-small-20260902 |
| Context window | 128,000 tokensAbout 96,000 English words |
| Max output | 8,192 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 12 Sep 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | No |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Schematron V2 Small yet.
Compare Schematron V2 Small
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.