All models
Inference Net
Schematron V2 Small fastruns locally
inference-net/schematron-v2-small
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...
Input / 1M
$0.050
USD per million tokens
Output / 1M
$0.23
USD per million tokens
Est. cost / token
$0.000000095
$0.095 per 1M, 3:1 mix
Context window
128K
max output 4K
Major features
Open weightsCachingJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 2.6 GB |
| Q3_K_M | fair | 2.9 GB |
| Q4_K_Mrecommended | good | 3.2 GB |
| Q5_K_M | very good | 3.6 GB |
| Q6_K | excellent | 3.9 GB |
| Q8_0 | near-lossless | 4.7 GB |
| F16 | lossless | 7.6 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.050 | $0.23 | $0.050 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.050
- Output
- $0.23
- Cached input
- $0.050
- Blended (3:1)
- $0.095
Details
- Company
- Inference Net
- Version
- 2
- Family
- Schematron
- Released
- 2026-09-12
- Parameters
- 3B
- Max output
- 4K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 32 min ago