Schematron V2 Small vs Schematron V2 Turbo
Schematron V2 Small (Inference.net) and Schematron V2 Turbo (Inference.net) are listed at different prices. Schematron V2 Turbo costs less: $0.03 per 1M input tokens and $0.15 per 1M output tokens, against $0.05 and $0.23 for Schematron V2 Small. Both hold 128,000 tokens of context. Both accept text and produce text.
Inference.net: Schematron V2 Small and Schematron V2 Turbo both accept and produce text, support structured outputs and response formats, and have 128,000-token context windows with 8,192-token output limits. Small prioritizes extraction quality for complex schemas and long pages, while Turbo prioritizes throughput for high-volume extraction.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Schematron V2 Small | Schematron V2 Turbo |
|---|---|---|
| Maker | Inference.net | Inference.net |
| Added to catalog | 12 Sep 2026 | 12 Sep 2026 |
| Input, per 1M tokens | $0.05 | $0.03 |
| Output, per 1M tokens | $0.23 | $0.15 |
| Cached input read, per 1M | $0.05 | $0.03 |
| Context windowTokens | 128,000 | 128,000 |
| Max outputTokens | 8,192 | 8,192 |
| Accepts | text | text |
| Produces | text | text |
| Tool calling | No | No |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Schematron V2 Small | Schematron V2 Turbo |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0001 | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0014 | $0.0009 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0020 | $0.0012 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0078 | $0.0047 |
Which to choose
Choose Schematron V2 Small if
No row of the table favours Schematron V2 Small. The difference, if there is one, is in the answers it writes: try it on your own task.
Schematron V2 Small detailsChoose Schematron V2 Turbo if
- Input tokens cost less: $0.03 against $0.05 per 1M
- Output tokens cost less: $0.15 against $0.23 per 1M
- Cached input costs less: $0.03 against $0.05 per 1M
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.