scaledown/extract

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-10-13 收录该模型(收录时间不等于模型正式发布日期);上下文:1,000,000 tokens;输入价:$0.0400/百万 tokens;输出价:$0.0000/百万 tokens;定位(来源描述):Extract is a description-driven entity extraction model from ScaleDown.

全文

ScaleDown: Extract

scaledown/extract

Compare

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through provider.options.scaledown.entities, and the model returns each matching span with a confidence score, character offsets, and surrounding context. It is suited for pulling structured values out of contracts, invoices, emails, and transcripts, and includes built-in OCR so scanned images and PDFs work without a separate step.

Learn more in ScaleDown's docs: https://docs.scaledown.ai/api-reference/extract-overviewOpens in new tab

Modalities

In / out price

20% off

$0.04 / $0per 1M

Context

1.0M

Released

Oct 13, 2026

Compare

Playground

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput

20% off

$0.05$0.04Free0.71s142 tok/s

98.26%

Provider20% offInput / Output /M

Input $0.04 / Output Free20% off

142 tok/s98.26% 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

$0.04486/M tokens

Output

$0/M tokens

Extract — Price history

Price history

No effective price data for this selection

$0.0449$0.000.0%100.0%

ProviderInput / Output /M

Token share

Effective in $0.0449 / Effective out $0.00

Token share

100.0%

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

142tok/s

P50, best across providers

Latency

0.71s

P50, best provider

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.

99.57%

Availability over the last 3 days

Last 72 hours

Availability 99.57%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.96%

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.

AlphaLens

new

667Mtokens

2.

Project Passport ScaleDown

new

37.6Mtokens

3.

Hermes Agent

new

14.8Mtokens

4.

rinkats decision round

new

13.9Mtokens

5.

ugrit-agent-pipeline

new

13.4Mtokens

Rest of OpenRouter

60.7M

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 ScaleDown: Extract on OpenRouter.

Extractions APIGuide

Extract Invoice Fields with ScaleDown ExtractCookbook

Introducing the Extractions APIBlog post

Frequently asked questions

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through provider.options.scaledown.entities, and the model returns each matching span with a confidence score, character offsets, and surrounding context.

The Extract documentation on OpenRouter includes the Extractions API guide, the Extract Invoice Fields with ScaleDown Extract cookbook, and the Introducing the Extractions API blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Extract costs $0.04/M input tokens and $0.00/M output tokens.

Extract has a 1,000,000 token context window.

No. Extract does not accept tools, so function calling is unavailable. It does not support response_format, so JSON output is not enforced.

Extract accepts text, images, and files such as PDFs as input and returns text.

Extract is served by 1 provider on OpenRouter: ScaleDown.

Summarize and Classify-1 are other text models from Scaledown.

Extract was released on October 13, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报