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.

New here? See how it works A 1-minute tour of the playground, models and your API key.

Free Models Router vs Extract: API price, context & features · api14

Free Models Router vs ScaleDown: Extract

A side-by-side comparison of Free Models Router (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

	Free Models Router	ScaleDown: Extract
Provider	OpenRouter	ScaleDown
Input	-	$0.14 / 1M tokens
Context window	200,000	1,000,000
Max output	-	900,000
Input	text, image	text, image, file
Output	text	text
Tool calling
Structured output
Reasoning control
Added	Feb 1, 2026	Oct 13, 2026

Key differences

ScaleDown: Extract reads 5.0× more context (1,000,000 tokens).
Only Free Models Router supports tool calling.
Only Free Models Router supports structured JSON output.
Only Free Models Router supports reasoning effort control.

In depth

Free Models Router is a text model from OpenRouter, listed under the model id openrouter/free. ScaleDown: Extract is a text model from ScaleDown, listed under the model id scaledown/extract. Both take text and image input and both return text output, so at the level of basic shape they are doing the same job: you send content in, you get text back. The differences show up in how much you can send and how much control you have over the response.

The clearest split is context. ScaleDown: Extract carries a context window of 1,000,000 tokens against 200,000 for Free Models Router, so ScaleDown is the one to reach for when the material is long. ScaleDown also accepts file input alongside text and image, while Free Models Router accepts text and image only. In the other direction, Free Models Router exposes a wide set of parameters: temperature, top_p, top_k, min_p, frequency and presence penalties, repetition penalty, seed, stop, logprobs and top_logprobs, response_format, structured_outputs, tool_choice and tools, plus reasoning controls such as reasoning, reasoning_effort and include_reasoning. ScaleDown: Extract supports max_tokens only. So Free Models Router is the model with tool calling, structured output and reasoning controls, and ScaleDown is the model with the larger window and file input.

For practical work, pick ScaleDown: Extract when the task is extraction or summarisation over very large inputs, especially when those inputs arrive as files, and when a plain text answer is all you need. Pick Free Models Router when the task needs function calling, a JSON schema you can rely on, or explicit reasoning effort, and when the input fits comfortably inside 200,000 tokens. If your pipeline depends on sampling controls like seed or temperature, or on log probabilities for scoring, Free Models Router is the only one of the two that offers them.

Calling either through api14 is the same call. Both are served behind the OpenAI-compatible endpoint, so you keep your existing client, your messages array and your authentication, and change only the model id in the request body, between openrouter/free and scaledown/extract. Nothing else in the request shape needs to move, though you should drop parameters the target model does not list, since ScaleDown: Extract accepts max_tokens only.

There is a case where the smaller model still wins. If your job is a short prompt that needs tools, structured output or reasoning effort, the extra context of ScaleDown: Extract buys you nothing, and Free Models Router is the better fit. The qualitative price fields for input and output are not meaningfully different between the two, so cost is not the deciding factor here; context size, file input and parameter support are.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "openrouter/free" to "scaledown/extract" and prompts, streaming and tools keep working.

Free Models Router details & playground →ScaleDown: Extract details & playground →

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);

Free Models Router vs ScaleDown: Extract

Specifications

Key differences

In depth

Switch with one string

More comparisons