Schematron V2

by inference-net · family schematron

Facts

Release date	2026-09-12
Retired date	—
Knowledge cutoff	—
Context (max)	128,000
Max output	—
Modalities	text → text
Aliases	`schematron-v2schematron`
Open weights	no
Description	Inference.net's 3B-parameter HTML-to-JSON extraction model: reads a page and returns schema-constrained JSON — extraction instructions go in response_format, not the prompt. 128K context, $0.03-$0.05 in / $0.15-$0.23 out per Mtok depending on SKU. Not a chat model; Specialist extraction (small = quality on complex schemas/long pages, turbo = throughput).

Unknown values are shown as —.

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
OpenRouter	`inference-net/schematron-v2-small`		chat-completions	openai-chat	ga	0.05 / 0.23	none · default off · returns hidden
OpenRouter	`inference-net/schematron-v2-turbo`	turbo	chat-completions	openai-chat	ga	0.03 / 0.15	none · default off · returns hidden

Reasoning controls

OpenRouter· inference-net/schematron-v2-small· chat-completions none

none · default off · returns hidden

OpenRouter· inference-net/schematron-v2-turbo· chat-completions none

none · default off · returns hidden

Example requests

OpenRouter · openai-chat · inference-net/schematron-v2-small

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "inference-net/schematron-v2-small",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "inference-net/schematron-v2-small",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "inference-net/schematron-v2-small",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

OpenRouter · openai-chat · inference-net/schematron-v2-turbo

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "inference-net/schematron-v2-turbo",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "inference-net/schematron-v2-turbo",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "inference-net/schematron-v2-turbo",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())