Summarize
Summarize is a large language model made by ScaleDown, added to the catalog on 13 Oct 2026. It has a context window of 1,000,000 tokens and costs $0.04 per 1M input tokens and $0 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: summarising long documents, condensing lengthy text and creating rewritten summaries.
Price checked ยท source: OpenRouter
What Summarize is
ScaleDown: Summarize is an abstractive summarization model from ScaleDown. It is intended to condense long text and documents into shorter text, producing a fluent rewrite rather than simply lifting sentences from the source. The model accepts text, images, and files, and produces text. Its listing describes it as a summarization model; it does not provide further detail about how each input type is handled or what controls are available for shaping a summary.
The model has a context length of 1,000,000 tokens and a maximum output of 4,000 tokens. Its large stated context is suited to working with extensive source material, while the output limit sets the maximum length of the text it can produce in one response. The catalog positions it for condensing long text and documents, so relevant tasks include creating shorter versions of lengthy material and summarizing documents. The output is described as a rewrite, which distinguishes the stated approach from one that simply selects sentences from the source. The listing does not specify particular document formats, summary styles, or other supported features, so those capabilities should not be assumed. Its stated input and output types and context size provide the main details for deciding whether it fits a summarization task involving substantial source material.
Key features
- Abstractive summarization of long text and documents
- Accepts text, images, and files
- Produces text
- Has a 1,000,000-token context length
- Supports outputs up to 4,000 tokens
Typical uses
- Summarising long documents
- Condensing lengthy text
- Creating rewritten summaries
Summarize pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.04 |
| Output, per 1M tokens | $0 |
No price change since it was added on 13 Oct 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0000 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0010 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0012 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0060 |
Summarize specifications
| Model id | scaledown/summarize |
|---|---|
| Version | summarize-20260928 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 4,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 13 Oct 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | No |
| Structured outputs | No |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Summarize yet.
Compare Summarize
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.