Last verified
HTML TO JSONTHROUGHPUT TIER8K MAX OUTPUT128K CONTEXTCLOSED WEIGHTS

Schematron V2 Turbo API Pricing

Schematron V2 Turbo is the throughput tier of Inference.net's extraction models: raw HTML and a JSON Schema in, schema-valid JSON out, no prompt. It costs $0.03/M input and $0.15/M output, and a cache read bills at the input rate. Inference.net measures it at 4.14 requests per second on one H100 against 2.47 for Schematron V2 Small, which scores slightly higher on the vendor's own quality test.

Input - per 1M tokens
$0.03/M
V2 Small $0.05/M the HTML
Output - per 1M tokens
$0.15/M
V2 Small $0.23/M the JSON
Cached input - per 1M tokens
$0.03/M
Same as input - no cache discount 0% off
Effective - agentic blend
$0.0396/M
92/8 split - cache hits cost the same
§ 01 / TERMINAL

Run the numbers.

Calculator pre-loaded with Schematron V2 Turbo's rates. There is no cache setting: Inference.net bills a cache read at the input rate, so caching changes nothing. Input is where the money goes in extraction - the HTML is usually many times the size of the JSON that comes back - so clean the page before you send it.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

PRODUCT PAGE

Product page to JSON

$0.00045/page
12,000 in - 600 out~222,222 pages/$100
LISTINGS

Results page to rows

$0.00135/page
30,000 in - 3,000 out~74,074 pages/$100
ARTICLE

Article with metadata

$0.00072/page
20,000 in - 800 out~138,888 pages/$100
LONG PAGE

Long page, one schema

$0.003/page
90,000 in - 2,000 out~33,333 pages/$100
§ 03 / TOKENIZER

Paste text. See tokens. See cost.

What's a token →
Estimate · schematron-tokenizer-estimate · ≈3.75 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 326
Words 58
Tokens (estimated) 87 tokens
Cost as input · uncached $0.000003 USD
Cost as output · uncached $0.00001 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Schematron V2 Turbo Current $0.03 cache $0.03 $0.15 $0.0396 agentic 92/8 128K High-volume HTML-to-JSON extraction
Schematron V2 Small $0.05 cache $0.05 $0.23 $0.0644 +63% 128K Higher quality on complex schemas
Ministral 3 3B $0.10 cache $0.01 $0.10 $0.0321 −19% 128K A general 3B model at one flat rate
GPT-6 Luna $0.10 cache $0.01 $0.50 $0.0682 +72% 1.05M OpenAI's small tier with structured outputs
GLM-5.3-Flash $0.15 cache $0.03 $0.50 $0.0875 +2.2× 1M A general flash model with image input
MiMo-V2.6-Flash $0.14 cache $0.0028 $0.28 $0.0477 +20% 1M Cheap multimodal flash with deep cache discount

Frequently asked.

What Schematron V2 Turbo costs, what it gives up against Small, and what Inference.net does not price.

Q · 01 How much does Schematron V2 Turbo cost? +
$0.03/M input and $0.15/M output on Inference.net's model page, with cache reads at the input rate. On our 92/8 blend that is $0.0396/M, the lowest rate of any model Inference.net trains itself.
Q · 02 How do you call it? +
Through Inference.net's OpenAI-compatible API at https://api.inference.net/v1. Send the page's HTML as the user message and your schema as a JSON Schema in response_format; the model does not read system or user prompts, so the schema's field names and descriptions are the whole instruction. Inference.net recommends stripping scripts, styles and boilerplate with lxml first, which also cuts the input tokens you pay for.
Q · 03 Turbo or Small? +
Turbo when volume and speed decide it: Inference.net measures 4.14 requests per second on one H100 against 2.47 for Small, it allows 8K output tokens against Small's 4K, and it costs less per token. Small when the schema is complex or the page is long: the vendor scores it 4.060 against Turbo's 4.039 on its own GPT-5.4-judged 1-5 scale. Both figures are the vendor's and have not been reproduced independently.
Q · 04 Why does prompt caching not lower the bill? +
Because Inference.net prints a cache-read rate equal to the input rate for both Schematron V2 models. A cached token costs the same as a fresh one, so the effective rate on this page is simply the blend of input and output, whatever cache-hit rate you assume. For extraction that rarely matters: every page is new HTML, so there is little to cache anyway.
Q · 05 Has the price changed since launch? +
The input rate has, without an announcement we could find. The April 16, 2026 launch post priced Turbo at $0.06 input and $0.15 output per 1M; the earliest Internet Archive capture of the model page, May 18, reads $0.03 input and the same output, and it has not moved since.
Q · 06 Are the weights open? +
No. The April 2026 launch post says V2 Small and V2 Turbo stay closed-source and are served only through Inference.net's API. The first generation, Schematron-3B and Schematron-8B, is open on Hugging Face (released August 2025), but those two are no longer on Inference.net's serverless model list, so there is no per-token price for them.
Q · 07 What are the rate limits, and is there a batch discount? +
Inference.net's API docs list 30 requests per minute on the free tier, 250 once you buy credits, and 1,000 on the Growth and Enterprise plans. The async endpoint (/v1/slow) and the Batch API complete within 24 hours and are described as significantly cheaper, but no rate is published for either, so this page does not model a discount.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against inference.net · Last verified Sep 24, 2026
Methodology Report a correction More by Y.V.