Schematron V2 Small

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...

InputText
OutputText
Input / Outputclub$0.053 / $0.2438per 1M tokens · USD
Context window128Ktoken
Maximum output4.1Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.053/ 1M token
Cache readUS$0.053/ 1M token
OutputUS$0.2438/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
Text
Output
Text
Context window
128,000 token
Maximum output
4,096 token

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Schematron V2 Small, and who develops it?

Schematron V2 Small is a model from inference-net. Its model ID on Vecbase is 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...

How much does Schematron V2 Small cost on Vecbase?

For Schematron V2 Small, the Club plan lists USD 0.053 per 1 million input tokens and USD 0.2438 per 1 million output tokens, as of 10/22/2026, 9:26:00 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Schematron V2 Small’s context window?

Schematron V2 Small has a context window of 128,000 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Schematron V2 Small?

Schematron V2 Small can generate up to 4,096 tokens per response. Your API or request settings may set a lower limit.

Does Schematron V2 Small support structured outputs?

Yes. Schematron V2 Small supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Schematron V2 Small support?

Schematron V2 Small accepts Text and produces Text.

Which providers make Schematron V2 Small available through Vecbase?

Vecbase offers Schematron V2 Small through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Schematron V2 Small?

Use inference-net/schematron-v2-small as the model identifier for Schematron V2 Small. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

What does an agent need to access Schematron V2 Small through Vecbase?

To use Schematron V2 Small, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Schematron V2 Small?

We do not yet have a confirmed release date for Schematron V2 Small.

Which models can I compare with Schematron V2 Small on Vecbase?

You can compare Schematron V2 Small with Schematron V2 Turbo (inference-net/schematron-v2-turbo), Vecbase Flash (vecbase-1.0-lite), and Vecbase (vecbase-1.0). Check their capabilities and prices to find the best fit for your task.