Inference-net

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...

Context Window
128K tokens
Parameters
3B
Input Price
$0.05/1M
Output Price
$0.23/1M
Price Tier
budget
Provider
Inference-net

How to Use Inference.net: Schematron V2 Small

With CoreAI, you can start chatting with Inference.net: Schematron V2 Small instantly — no separate subscription needed. CoreAI lets you chat with Inference.net: Schematron V2 Small alongside 300+ other AI models from Inference-net and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select Inference.net: Schematron V2 Small from the model selector
  3. Start chatting, comparing, or creating with AI

Inference.net: Schematron V2 Small at a Glance

Measured against all 428 chat models CoreAI serves, Inference.net: Schematron V2 Small sits at #358 for context capacity — 128K tokens, roughly 96,000 words or 192 pages of text in a single conversation. On price, it is the #18 cheapest of 141 budget-tier models by input cost. Released 2026-09-12, it is one of the 2 newest additions to the catalog.

Inference.net: Schematron V2 Small Compared to Its Closest Alternatives

SpecInference.net: Schematron V2 SmallInference.net: Schematron V2 TurboByteDance: UI-TARS 7B IBM: Granite 4.0 Micro
ProviderInference-netInference-netBytedanceIbm-granite
Input $/1M tokens$0.05$0.03$0.1$0.017
Output $/1M tokens$0.23$0.15$0.2$0.112
Context window128K128K128K131K
Reasoning modeNoNoNoNo
Image inputNoNoYesNo
Price tierbudgetbudgetbudgetbudget

Every model in this table is available on CoreAI — open the web app and run the same prompt through Inference.net: Schematron V2 Small and Inference.net: Schematron V2 Turbo side by side to judge with your own eyes.

What Inference.net: Schematron V2 Small Actually Costs in Practice

A typical question (about 1,000 tokens in, 500 out) runs $0.00016 on Inference.net: Schematron V2 Small's raw per-token rates; a heavy session with a 50K-token document costs about $0.004. On CoreAI you don't juggle these numbers — one subscription covers Inference.net: Schematron V2 Small and 300+ other models under a plan usage limit, with no API keys. See plans.

More Inference-net Models

Inference-net

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
128K budget

Frequently Asked Questions about Inference.net: Schematron V2 Small

What is Inference.net: Schematron V2 Small's context window?

Inference.net: Schematron V2 Small handles 128K tokens of context — roughly 96,000 words, or about 192 pages of text in one conversation.

How much does Inference.net: Schematron V2 Small cost?

Inference.net: Schematron V2 Small's underlying rates are $0.05 per 1M input tokens and $0.23 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.

Can Inference.net: Schematron V2 Small process images?

No — Inference.net: Schematron V2 Small is text-only. If you need image understanding, its budget-tier peers with vision are listed in the comparison table above.

Does Inference.net: Schematron V2 Small support reasoning or thinking mode?

No — Inference.net: Schematron V2 Small answers directly without an extended reasoning phase, which usually means faster responses.

How can I use Inference.net: Schematron V2 Small without an API key?

Open the CoreAI web app or the iOS/Android app, pick Inference.net: Schematron V2 Small in the model selector, and chat — no API key, no per-token billing. One subscription covers Inference.net: Schematron V2 Small and 300+ other models.

What are the best alternatives to Inference.net: Schematron V2 Small?

The closest alternatives on CoreAI are Inference.net: Schematron V2 Turbo, ByteDance: UI-TARS 7B , IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.

Try Inference.net: Schematron V2 Small Now

Chat with Inference.net: Schematron V2 Small and 300+ other AI models — all in one app.

Use Web App Download App →