We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
ScaleDown: Summarize
scaledown/summarizeTry ScaleDown: Summarize now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
ScaleDown: Summarize at a glance
- Input price is 91% lower than the median of 434 Text models.
- Context window of 1,000,000 tokens, enough for long documents and multi-turn conversations.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.000140.
About ScaleDown: Summarize
ScaleDown: Summarize is a text model from ScaleDown, listed on api14 under the model id scaledown/summarize. It belongs to the text category and is built specifically for summarization work. ScaleDown is the provider behind the model, and the provider describes it as an abstractive summarization model, meaning it produces a fluent, faithful rewrite of the source material rather than extracting sentences verbatim.
The model accepts text, images and files as input, and returns text only. Its context window is 1,000,000 tokens, which is large enough to hold very long documents in a single request, and its maximum output is 4,000 tokens. The supported request parameter is max_tokens. Because input can include images and files alongside text, you can send a document or a scanned page rather than pasting plain text, and the model will condense it into a written summary.
The practical uses follow directly from those traits. Long reports, contracts, research papers, meeting transcripts and multi document collections can be reduced to a short readable summary without manual skimming. Since the output is an abstractive rewrite, the result reads as coherent prose instead of a set of lifted sentences, which suits briefings, executive summaries and digests. The large context window means you can pass an entire document or a batch of related files in one call instead of chunking and stitching summaries together yourself, and the image input allows summarization of material that only exists as a screenshot or scan.
To call it through api14, use the OpenAI compatible chat completions endpoint with the model id scaledown/summarize, the same way you would call any other model on the gateway. Set max_tokens to control the length of the summary, up to the model's maximum output of 4,000 tokens. The model supports max_tokens as its request parameter, so keep your request body to that plus the usual messages array carrying your text, image or file input.
Keep the output ceiling in mind when planning. If you need a summary longer than 4,000 tokens, or you need a task other than summarization, a different model will fit better. Within those bounds, ScaleDown: Summarize is a straightforward choice for condensing long or mixed format input into fluent text.
How to call the ScaleDown: Summarize API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "scaledown/summarize".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "scaledown/summarize",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
max_tokensSpecifications
- Context length
- 1,000,000
- Max output
- 4,000
- Input
- text, image, file
- Output
- text
Requests on api14 · last 7 days
ScaleDown: Summarize: frequently asked questions
- How much does the ScaleDown: Summarize API cost?
- ScaleDown: Summarize costs Input $0.14 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of ScaleDown: Summarize?
- ScaleDown: Summarize reads up to 1,000,000 tokens per request: prompt, history and documents together. It writes up to 4,000 output tokens per response.
- What can ScaleDown: Summarize do?
- ScaleDown: Summarize accepts text, image, file and returns text.
- How do I call ScaleDown: Summarize from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "scaledown/summarize". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to ScaleDown: Summarize?
- Comparable Text models at a similar price: ScaleDown: Extract, Mistral: Mistral Nemo, Recursive: Flint (free). Each runs through the same API key, so switching is one string.
ScaleDown: Summarize community
New topicThis community has no topics yet. Open the first one about ScaleDown: Summarize.