Can I run Summarize locally?

No — ScaleDown has not released open weights, so Summarize is available only through their API.

What does Summarize cost and how long is the context?

Input is priced at $0.04 per million tokens and output is free; the context window is one million tokens.

How is Summarize different from using a general-purpose model to summarize?

It is a purpose-built abstractive model with fixed sampling tuned for faithful output, rather than a general model you prompt into summarization mode — and the free output pricing makes it cheaper for high-volume document pipelines.

Summarize

3926°

#llm #scaledown #vision #summarization #long context #budget

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

ScaleDown | 1,000,000 token context | $0.04/M input, free output. Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for document review, transcript digests, and RAG pre-processing where retrieved content must be shortened before reaching another model. Format, focus, language, and length are steered through the system prompt, while sampling is fixed to a configuration tuned for faithful output. Learn more in ScaleDown's docs: https://docs.scaledown.ai/api-reference/summarize-overviewOpens in new tab

Guides for this model

Open weights vs open source vs API-only: what you are actually allowed to do

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Summarize is a purpose-built abstractive summarization model from ScaleDown. Rather than extracting sentences verbatim, it rewrites source material into a coherent, faithful condensed form — useful for document review, meeting transcripts, and trimming retrieved chunks before they hit a downstream model. With a one-million-token context window and near-zero input cost, it handles long documents without chunking gymnastics.

Known for

Abstractive rewrites: condenses text rather than copy-pasting sentences from the source.
One-million-token context window handles very long documents in a single pass.
Tuned sampling configuration aimed at faithful, low-hallucination output.
System-prompt steering for format, focus, language, and output length.
Designed as a RAG pre-processing step to shrink retrieved content before a main model sees it.

Watch out for

Closed weights, API-only — you cannot run this locally or inspect the model.
Sampling is fixed by the maker; you cannot adjust temperature or other generation parameters yourself.
Tagged as a vision model, but the published description covers only text summarization — the vision capability is not documented.

Best for

Prompts to try

Condense a long report

Summarize the following report into a single paragraph of no more than 100 words. Preserve the key findings and any numerical results. Do not include background or methodology unless it directly affects the conclusions. [Paste your report text here]

Digest a meeting transcript

You are given a meeting transcript. Produce a structured digest with three sections: Decisions Made, Action Items (owner and deadline if mentioned), and Open Questions. Keep the whole digest under 200 words and write in plain prose, not bullet points.

Shrink a chunk for RAG

The following passage is a retrieved document chunk that will be passed to another model. Rewrite it to retain only the information relevant to this question: What are the main risks associated with the proposed acquisition? Keep the rewrite under 150 words and preserve any figures or named entities.

Compare with

Extract
API-only model
1,000,000 token context · $0.04/M input, free output
Step 5 Preview
Open-weights model
1,048,576 token context · $1.00/M input, $2.70/M output
Qwen3 VL 8B Instruct
Open-weights model
262,144 token context · $0.25/M input, $0.75/M output
Qwen3 VL 30B A3B Instruct
Open-weights model
262,144 token context · $0.15/M input, $0.60/M output

More text models from scaledown

Questions people ask

Can I run Summarize locally?: No — ScaleDown has not released open weights, so Summarize is available only through their API.
What does Summarize cost and how long is the context?: Input is priced at $0.04 per million tokens and output is free; the context window is one million tokens.
How is Summarize different from using a general-purpose model to summarize?: It is a purpose-built abstractive model with fixed sampling tuned for faithful output, rather than a general model you prompt into summarization mode — and the free output pricing makes it cheaper for high-volume document pipelines.

Captain's verdict
A narrow, cheap tool that does one thing well — if summarization or RAG pre-processing is your bottleneck, the economics are hard to argue with.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Summarize is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm scaledown vision summarization long context budget research

Browse by Model Family