Dots Studio: Dots3-Note Preview (free) vs ScaleDown: Extract
A side-by-side comparison of Dots Studio: Dots3-Note Preview (free) (Free) and ScaleDown: Extract ($0.14 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.
Specifications
| Dots Studio: Dots3-Note Preview (free) | ScaleDown: Extract | |
|---|---|---|
| Provider | Dots Studio | ScaleDown |
| Input | - | $0.14 / 1M tokens |
| Context window | 512,000 | 1,000,000 |
| Max output | 460,800 | 900,000 |
| Input | text, image | text, image, file |
| Output | text | text |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Aug 14, 2026 | Oct 13, 2026 |
Key differences
- ScaleDown: Extract reads 2.0× more context (1,000,000 tokens).
- Only Dots Studio: Dots3-Note Preview (free) supports tool calling.
- Only Dots Studio: Dots3-Note Preview (free) supports structured JSON output.
- Only Dots Studio: Dots3-Note Preview (free) supports reasoning effort control.
In depth
Dots Studio: Dots3-Note Preview (free) is a text model from Dots Studio, released as a preview under a free tag. ScaleDown: Extract comes from ScaleDown and is also a text model, positioned around extraction style work. Both are served through api14 alongside each other, so the choice between them is mostly about what your task needs rather than about access.
The two differ most in context and in what you can ask of them. ScaleDown: Extract has the larger context window, at one million tokens against 512,000 for Dots3-Note Preview, so it can take in substantially longer inputs in a single call. On input modalities, Dots3-Note Preview accepts text and images, while ScaleDown: Extract accepts text, images and files, giving it one more way to receive content. Where Dots3-Note Preview pulls ahead is in control: it is the only one of the two that supports tools, structured outputs and reasoning, and it exposes a wider parameter set including temperature, top_p, max_tokens, response_format, tool_choice, include_reasoning and reasoning. ScaleDown: Extract supports only max_tokens, so you get far less steering over how it responds. Both output text only.
For practical work, reach for Dots3-Note Preview when you need the model to call functions, return structured or schema shaped output, or reason through a problem before answering, and when you want to tune sampling behaviour. It also handles image input, so mixed text and image prompts are fine. Reach for ScaleDown: Extract when the job is primarily about ingesting a very large body of material, especially when that material arrives as files, and when you only need a straightforward text result without tool calls or structured formatting. If your input fits inside 512,000 tokens and you do not need tools, structured outputs or reasoning, either model can serve, and the price table on this page is the place to check relative cost before deciding.
Calling either model through api14 works the same way, because the API is OpenAI compatible. You point your client at the api14 base URL, send your request in the usual chat completions shape, and set the model field to the id you want. Switching between them means changing only that id, between "dots-studio/dots-3-note-preview:free" and "scaledown/extract". Your surrounding code, authentication and request structure stay as they are, though you should keep in mind that ScaleDown: Extract accepts only max_tokens among the listed parameters, so any temperature, top_p, tool or response_format fields you send for the other model will not apply to it.
There are still cases where ScaleDown: Extract is the better pick even if you like the feature set of Dots3-Note Preview. If your document is longer than 512,000 tokens, or if it arrives as a file you would rather pass through directly, the larger context and the file input make ScaleDown: Extract the more natural fit, and its narrower parameter surface keeps the call simple when all you want is extracted text back.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "dots-studio/dots-3-note-preview:free" to "scaledown/extract" and prompts, streaming and tools keep working.
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/extract",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
More comparisons
- LiquidAI: LFM3-1.7B vs Ricursive: Ripple 65B Preview
- LiquidAI: LFM3-1.7B vs Crouton Alpha
- LiquidAI: LFM3-1.7B vs Tencent: Hy4
- LiquidAI: LFM3-1.7B vs Z.ai: GLM 5.3 FlashX Legal
- Ricursive: Ripple 65B Preview vs Crouton Alpha
- Ricursive: Ripple 65B Preview vs Tencent: Hy4
- Ricursive: Ripple 65B Preview vs Z.ai: GLM 5.3 FlashX Legal
- Crouton Alpha vs Tencent: Hy4