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.

Gemini 4 Argon vs Summarize: API price, context & features · api14

Google: Gemini 4 Argon vs ScaleDown: Summarize

A side-by-side comparison of Google: Gemini 4 Argon ($7.00 / 1M tokens) and ScaleDown: Summarize ($0.14 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Google: Gemini 4 Argon	ScaleDown: Summarize
Provider	Google	ScaleDown
Input	$7.00 / 1M tokens	$0.14 / 1M tokens
Output	$35.00 / 1M tokens	-
Cache read	$0.35 / 1M tokens	-
Cache write	$0.66 / 1M tokens	-
Reasoning	$35.00 / 1M tokens	-
Audio input	$7.00 / 1M tokens	-
Image	$0.000007 / image	-
Web search	$49.00 / 1K searches	-
Context window	1,048,576	1,000,000
Max output	943,718	4,000
Input	audio, file, image, text, video	text, image, file
Output	text	text
Tool calling
Structured output
Reasoning control
Added	Oct 13, 2026	Oct 13, 2026

Key differences

ScaleDown: Summarize is 98% cheaper on input tokens.
Only Google: Gemini 4 Argon supports tool calling.
Only Google: Gemini 4 Argon supports structured JSON output.
Only Google: Gemini 4 Argon supports reasoning effort control.
A request with 1,000 input and 500 output tokens costs $0.02 with Google: Gemini 4 Argon and $0.000140 with ScaleDown: Summarize.

In depth

Google: Gemini 4 Argon is a text model from Google, released on 2026-10-13. ScaleDown: Summarize is a text model from ScaleDown, released on the same date. Both are served through api14 under the model ids google/gemini-4-argon and scaledown/summarize, and both return text as their output.

The two differ most in what they accept and what they let you control. Gemini 4 Argon takes audio, file, image, text and video as input, while ScaleDown: Summarize takes text, image and file. Their context windows are close enough that neither is meaningfully bigger, so the choice is not about fitting a longer document. The parameter lists are where they really separate. Gemini 4 Argon supports tools and tool choice, structured outputs, reasoning and reasoning effort, include_reasoning, response_format, seed, stop, temperature and top_p, alongside max_tokens. ScaleDown: Summarize supports max_tokens only. So Gemini 4 Argon is the one to reach for when you need function calling, JSON shaped output, or a reasoning pass, and ScaleDown: Summarize is the one to reach for when you just want text back.

For practical work, pick Gemini 4 Argon when the task involves more than plain text, such as a video or audio clip you want described or questioned, or when your pipeline depends on tools, structured outputs or reasoning. Pick ScaleDown: Summarize when the job is straightforward summarization or another plain text transformation over text, images or files, and you want a narrow, predictable call surface. ScaleDown: Summarize is the cheaper option on input, and output pricing is about the same, so for high volume input heavy work it can be the more economical choice. If your task needs any of the parameters only Gemini 4 Argon exposes, that settles it regardless of price.

Calling either model works the same way. Both are exposed through api14's OpenAI-compatible API, so you point your existing OpenAI client at the api14 base URL, send your key, and set the model field. To switch between them you change only that field, between google/gemini-4-argon and scaledown/summarize. Your request and response handling stay the same, with one caveat: if you send parameters that ScaleDown: Summarize does not support, such as tools or response_format, they will not take effect, so keep those calls to max_tokens.

There are cases where ScaleDown: Summarize is still the better pick even though Gemini 4 Argon is more capable. If your input is text, image or file and you only need text out, the extra modalities and parameters on Gemini 4 Argon buy you nothing, and the lower input price on ScaleDown: Summarize is a real advantage at volume. A summarization job that does not need tools, structured output or reasoning is exactly what ScaleDown: Summarize is built for, so defaulting to it there keeps your calls simple and your input costs down.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "google/gemini-4-argon" to "scaledown/summarize" and prompts, streaming and tools keep working.

Google: Gemini 4 Argon details & playground →ScaleDown: Summarize 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/summarize",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

Google: Gemini 4 Argon vs ScaleDown: Summarize

Specifications

Key differences

In depth

Switch with one string

More comparisons