inference-net
Inference.net: Schematron V2 Turbo
inference-net/schematron-v2-turbo
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog entry, inference-net/schematron-v2-turbo is a 3B-parameter text-to-text model from Inference.net described as specialized for HTML-to-JSON extraction, with throughput prioritized for high-volume workloads. The catalog states that extraction instructions must be supplied as a JSON schema via the response_format parameter, and reports a 128,000-token context window plus support for structured outputs and common sampling controls. No independent model card was available in this source pack, so all capability claims are source-reported rather than measured, and no benchmark results were listed.[1]
Strengths
- The OpenRouter catalog describes a purpose-built HTML-to-JSON extraction model optimized for throughput in high-volume pipelines.[1]
- It reports a large 128,000-token context window, which may suit extraction over long or deeply nested documents.[1]
- Structured outputs are enforced through a JSON schema in response_format, alongside sampling parameters such as temperature, top_p, and seed.[1]
Limitations
- All evidence comes from a single OpenRouter catalog entry; no independent model card or benchmark results were included in this source pack.[1]
- Extraction requires a JSON schema in response_format, so ad-hoc prompting without a schema is outside its documented workflow.[1]
- Knowledge cutoff, training details, and real-world extraction accuracy are not reported; validation on your own workloads is advisable.[1]
Where to use it
- Potentially a good fit for pipelines that convert large volumes of HTML pages or records into schema-constrained JSON at high throughput.[1]
- May suit teams already using schema-driven structured outputs who want a small, specialized extraction model rather than a general-purpose one.[1]
- Worth trialing on long HTML documents that benefit from the reported large context window, subject to workload-specific testing.[1]
Sources
- [1] OpenRouter catalog · Inference.net: Schematron V2 TurboSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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
- Model ID
- inference-net/schematron-v2-turbo
- Canonical ID
- inference-net/schematron-v2-turbo-20260902
- Creator
- inference-net
- Added to OpenRouter
- 12.09.2026
- Context length
- 128,000
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.030 / out $0.150
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| InferenceNetbf16 | 128,000 | $0.030 | $0.150 | — | — | 100% |
| InferenceNetbf16 | 128,000 | $0.030 | $0.150 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.