opendunes

Schematron V2 Turbo

by Inference NetReleased 12 September 2026

Schematron V2 Turbo turns the raw code behind a web page, up to 128 pages of it, into details laid out in the exact form you give it. That form carries the instructions; extra written requests do not. It is built for volume, so it fits jobs that pull the same fields from a large number of pages, and it can write twice as much as Schematron V2 Small (8 pages against 4).

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,035 DA per message3 000 DA buys about 85 000 messages

One message, the ordinary use

1 000 tokens sent× 9,99 DA per 1M0,010 DA
500 tokens back× 49,93 DA per 1M0,025 DA
Total≈ 0,035 DA

Every rate

Meter↑ you send↓ comes back
Text tokens9,99 DA49,93 DA
Cached tokens read9,99 DA

per 1M tokens

Extract a job listing into a fixed schema≈ 0,065 DA
Extract a news article's metadata≈ 0,070 DA
Turn one product page into JSON≈ 0,10 DA
Pull prices from a supplier's catalogue page≈ 0,27 DA
Turn a long directory page into JSON rows≈ 0,75 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

InferenceNetUnited States…
↑ Sent, per 1M
9,99 DA
↓ Back, per 1M
49,93 DA
Cache read
9,99 DA
Latency
…
Throughput
…
InferenceNet…
↑ Sent, per 1M
9,99 DA
↓ Back, per 1M
49,93 DA
Cache read
9,99 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
InferenceNetUnited States9,99 DA49,93 DA9,99 DA………
InferenceNet9,99 DA49,93 DA9,99 DA………

You pay the price of the provider that served your request. Prices read 15:48 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
inference-net/schematron-v2-turbo
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="inference-net/schematron-v2-turbo",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_bias

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Questions about Schematron V2 Turbo

  • How much does Schematron V2 Turbo cost in dinars?

    About 0,035 DA per message. ↑ 9,99 DA · ↓ 49,93 DA per 1M tokens.

  • Is Schematron V2 Turbo free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Schematron V2 Turbo best for?

    Schematron V2 Turbo turns the raw code behind a web page, up to 128 pages of it, into details laid out in the exact form you give it. That form carries the instructions; extra written requests do not. It is built for volume, so it fits jobs that pull the same fields from a large number of pages, and it can write twice as much as Schematron V2 Small (8 pages against 4).

  • Schematron V2 Turbo or Schematron V2 Small?

    Schematron V2 Small costs 0,020 DA more for the same message.

  • How do I pay for Schematron V2 Turbo without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Schematron V2 Turbo included, is paid from that balance. No foreign card, no conversion.

  • Does Schematron V2 Turbo work in Arabic, French or Darja?

    Inference Net names no languages for Schematron V2 Turbo. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 128K tokens in one request, about 120 pages. It writes up to 6 000 words at once.

  • Is Schematron V2 Turbo open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Schematron V2 Turbo, and when was it released?

    Inference Net. Released 12 September 2026.

Other Inference Net models, priced in dinars

See all Inference Net models
Schematron V2 SmallInference Net · Sep 12, 2026

HTML-to-JSON extraction against your own schema, tuned for quality on complex pages

120 pages at onceOpen weightsFills your JSON
≈0,055 DAper message
View model