Schematron Models

Unknown / Unverified
2 models2026Up to 125K ctxFrom $0.030/1M input

Last refreshed 2026-10-19. Next refresh: weekly.

Details

LicenseUnknown / Unverified
Commercial useUnknown
Models2
Released2026
Max context125K

Capabilities

Structured OutputsAll models

About

Inference.net Schematron HTML-to-structured-data extraction models (v2 Small / Turbo).

Decision facts

Best fit
extractionstructured outputs
Capability starting point
Schematron V2 Small with 125K context and structured outputs
Lowest tracked input
Schematron V2 Turbo · $0.030/1M · Inference.net
Closest related family
360Zhinao

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs extraction, 125K context, and 3B parameters.

2026-04extraction125K context3B parameters

Use when the workload needs extraction, 125K context, and 3B parameters.

2026-04extraction125K context3B parameters

Release Timeline

1 release group
2026-04
2 current
Schematron V2 Small
extraction125K context3B parameters
Current
Schematron V2 Turbo
extraction125K context3B parameters
Current

Specifications(2 models)

Schematron model specifications comparison
ModelReleasedContextParametersStructured Outputs
Schematron V2 Small2026-04125K3BYes
Schematron V2 Turbo2026-04125K3BYes

Available From(3 providers)

Pricing

Schematron model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Schematron V2 TurboInference.net$0.03$0.15Serverless
Schematron V2 TurboVercel AI Gateway$0.03$0.15Serverless
Schematron V2 TurboOpenRouter$0.03$0.15Serverless
Schematron V2 SmallInference.net$0.05$0.23Serverless
Schematron V2 SmallVercel AI Gateway$0.05$0.23Serverless
Schematron V2 SmallOpenRouter$0.05$0.23Serverless