inference-net/schematron-v2-small

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-09-12 收录该模型(收录时间不等于模型正式发布日期);上下文:128,000 tokens;输入价:$0.0500/百万 tokens;输出价:$0.2300/百万 tokens;定位(来源描述):Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net.

全文

Inference.net: Schematron V2 Small

inference-net/schematron-v2-small

Model weights

Compare

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 in response_format rather than through system or user prompts.

Modalities

In / out price

$0.05 / $0.23per 1M

Context

128K

Released

Sep 12, 2026

Compare

Playground

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

$0.05$0.23$0.050.30s312 tok/s

100.00%

$0.05$0.23$0.050.29s304 tok/s

100.00%

ProviderInput / Output /M

Input $0.05 / Output $0.23

312 tok/s100.00% uptime

Input $0.05 / Output $0.23

304 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.0496/M tokens

Output

$0.2207/M tokens

Schematron V2 Small — Price history

Price history

No effective price data for this selection

$0.0495$0.2190.0%53.7%

$0.0497$0.2220.0%46.3%

ProviderInput / Output /M

Token share

Effective in $0.0495 / Effective out $0.219

Token share

53.7%

Effective in $0.0497 / Effective out $0.222

Token share

46.3%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

312tok/s

P50, best across providers

Latency

0.28s

P50, best provider

Latency / throughput

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.94%

Availability over the last 3 days

Last 72 hours

Availability 99.94%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

100.00%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

DKP

new

95.4Mtokens

2.

Docfu

new

1.87Mtokens

3.

OpenRouter Ruby Client

new

1.68Mtokens

4.

Stock3 V17

new

1.32Mtokens

5.

yugos-evaluation

new

659Ktokens

Rest of OpenRouter

8K

Top 5 Apps

0

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Inference.net: Schematron V2 Small on OpenRouter.

Extractions APIGuide

Frequently asked questions

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 in response_format rather than through system or user prompts.

The Schematron V2 Small documentation on OpenRouter includes the Extractions API guide. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Schematron V2 Small costs $0.05/M input tokens and $0.23/M output tokens, with separate rates for Cache Read at $0.05/M tokens.

Schematron V2 Small has a 128,000 token context window. It supports up to 8,192 completion tokens.

No. Schematron V2 Small does not accept tools, so function calling is unavailable. It also supports structured outputs via a JSON schema in response_format.

Schematron V2 Small is served by 1 provider on OpenRouter: inference.net.

Schematron V2 Turbo is another text model from Inference Net.

Schematron V2 Small was released on September 12, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报