ScaleDown API
Access ScaleDown instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain AI like I'm five!", {
model: "scaledown/summarize"
}).then(response => {
console.log(response);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain AI like I'm five!", {
model: "scaledown/summarize"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of ScaleDown Models
ScaleDown Extract
scaledown/extract
ScaleDown Extract is a task-specific small language model from ScaleDown, an applied AI research lab that builds small models for compression, summarization, extraction and classification. Its name indicates it is intended for information extraction. The model has a 1,000,000-token context window with up to 900,000 output tokens. Input costs $0.04 per million tokens and output is free, so long documents can be processed at a low cost. ScaleDown has said its models are cheaper and faster than general-purpose large models for these narrow tasks. Those figures are the company's own and are not independently verified. It suits developers who need to pull specific facts or structured fields out of long documents, logs or transcripts without paying for a large general model. It accepts text input through the standard chat completions interface.
ChatScaleDown Summarize
scaledown/summarize
ScaleDown Summarize is a text summarization model from ScaleDown, a provider of task-specific small language models. It produces abstractive summaries, meaning the output is newly written text rather than extracted sentences. The last user message is treated as the source text. A system message can give instructions for the summary, and max_tokens limits its length. The result is returned as a JSON string with a summary key. The model accepts text only, has a 1,000,000-token context window, and produces up to 4,000 output tokens. Function calling and image or file inputs are not supported. Input is priced at $0.04 per million tokens and output is free, which makes long documents inexpensive to process. It suits applications that condense long documents, transcripts, articles, or support threads, and pipelines that need a summary step without a general-purpose chat model.
Frequently Asked Questions
The ScaleDown API gives you access to models for AI chat. Through Puter.js, you can start using ScaleDown models instantly with zero setup or configuration.
Puter.js supports a variety of ScaleDown models, including ScaleDown Extract and ScaleDown Summarize. Find all AI models supported by Puter.js in the AI model list.
With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.
Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.
Yes — the ScaleDown API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.