I
Compare
Schematron V2 Turbo
Inference.net · Released Sep 2026
A 3B-parameter model from Inference.net designed to extract structured data from HTML and unstructured text into JSON format using schema-based instructions.
- Strengths
- Optimized for high-throughput extraction workloads, handling large volumes of parsing and data structuring tasks with a 128k token context window.
- Best for
- Batch extraction jobs and production pipelines that need to convert HTML or text content into validated JSON structures at scale.
- Limitations
- As a smaller specialized model, it may struggle with complex reasoning, multi-step reasoning chains, or extraction tasks requiring deep semantic understanding beyond schema-constrained output.
Input / 1M
$0.03
Output / 1M
$0.15
Cached input / 1M
$0.03
Context window
128K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 13 Sep 2026 | $0.03 | $0.15 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 12 Sep 2026 | $0.03 | $0.15 | — | Imported from OpenRouter | openrouter.ai |