Active
Inference.net: Schematron V2 Turbo
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...
Context
128,000
Max output
8,192
Input / 1M
$0.03
Output / 1M
$0.15
Providers
4
01Profile
Profile
Released
2026-09-12
Last updated
2026-09-12
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 4 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
4+ recent events since 2026-09-12
2026-09-15Addedverceloffering→ new
2026-09-14Addednano-gptoffering→ new
2026-09-12Addedkilooffering→ new
2026-09-12Addedopenrouteroffering→ new