Gemini 4 Argon vs Flash: 2.7× the Price per Token, Yet Cheaper in Our 3-Task API Test

In our Gemini 4 Argon vs Flash test, the more expensive model came out cheaper: Gemini 4 Argon costs 2.7 times as much per token as Gemini 3.8 Flash, yet it finished three office tasks for $0.00687 against Flash's $0.01135, and in 12.5 seconds against 21.6. Flash still scored better, 15/15 against Argon's 14/15, because Argon's customer email went over a 120-word limit.

Tested on 14 October 2026, calling the Gemini API directly with gemini-3.8-flash and gemini-4-argon, each at its default thinking level. Each task ran once, so this is a real-world observation, not statistics. The tasks use made-up data. Prices come from the official Gemini API pricing page (updated 13 October 2026, paid tier).

Watch the real test run (Vietnamese narration): https://youtu.be/ygVlHxkqv7g

The test was run in Vietnamese: the tasks, the made-up data (amounts in Vietnamese dong) and the model replies are in Vietnamese, as are the screenshots below. So this is also a comparison on non-English content. We used the same three tasks as our Claude Haiku 5.5 vs Sonnet 5.5 test, graded every answer with code against answers worked out in advance, and measured real time and cost.

Key results

• Accuracy: Gemini 3.8 Flash 15/15 checks passed, Gemini 4 Argon 14/15 (its email was 124 words against a 120-word limit).
• Speed: Argon finished all three tasks in 12.5 seconds, Flash in 21.6 seconds.
• Cost: Argon $0.00687 for the three tasks, Flash $0.01135, despite Argon's 2.7× higher price per token.
• Why: Argon used 555 output tokens (thinking included) across the three tasks, Flash used 2,912.
• Caveat: Argon's introductory price doubles on 1 December 2026; at that price the same run would cost about $0.0137, slightly more than Flash.

Gemini 4 Argon vs Gemini 3.8 Flash: pricing and specs

Gemini 4 Argon is Google's strongest model and is newly available on the API. Both models are listed as "Stable" on the Gemini API models page. According to the pricing page, Argon is not available on the Free tier or on the Google AI Pro plan. Sources: Gemini API pricing and the Gemini API models page, which also has Google's own description of Argon.

How we tested Gemini 4 Argon vs Flash

1. Three office tasks, identical to the Haiku vs Sonnet test, with answers worked out before running:
   • Invoice extraction: read a messy email and extract invoice details as JSON. Traps: a mistyped amount that was later corrected, a former company name, a due date written in words.
   • Tiered commission: work out sales commission for 5 staff at 2% / 4% / 6% by band, plus a 1 million dong bonus for sales of 150 million dong or more with no returned orders. Traps: Dũng at exactly 200 million, Hạnh at 149.5 million (500,000 short of the bonus), Chi with enough sales but one returned order.
   • Customer reply: write to a customer whose order was late, in at most 120 words, with a 10% discount code, no promised delivery date, ending with the hotline.
2. The same prompt sent through the Gemini API to each model, at its default thinking level.
3. Code grades every item: 5 invoice fields, 6 commission figures, 4 email conditions. That is 15 items per model.
4. Real measurements: time from request to response, token counts reported by the API (output includes thinking tokens), and cost from the price list.

Results task by task

Task 1: extracting invoice details

Both models returned the same JSON, with all 5 fields right: tax code, pre-tax amount of 12,450,000 dong (not the mistyped figure), tax of 996,000 dong, total of 13,446,000 dong, and due date 24/10/2026. Times were almost the same: Flash 4.2 seconds, Argon 3.9 seconds. The difference was output tokens: Flash used 490, Argon 147, for an identical answer.

Task 2: tiered sales commission

Both got all 6 figures right, neither wrongly gave Hạnh the bonus, and both followed the "No explanation" instruction by returning only the table. But Flash took 8.1 seconds and 1,322 output tokens, while Argon took 4.6 seconds and 234.

Task 3: replying to a customer

This was the only task where the outcome differed. Flash wrote 96 words and passed all 4 checks. Argon wrote 124 words, over the 120-word limit. It also put "Trân trọng," ("Kind regards") after the hotline even though the task said to end with the hotline; our code only checks that the hotline is present, not where, so that slip did not cost it a point. Both included the 10% code and promised no delivery date.

Gemini 4 Argon vs Flash: which one wins overall?

So the Gemini 4 Argon vs Flash result runs against the price list: Argon was cheaper and faster in this run but missed one check, and Flash was the only model with a perfect score.

Why did the more expensive Gemini model cost less?

You pay per token, and thinking tokens are billed as output tokens. In this run Flash used 490, 1,322 and 1,100 output tokens across the three tasks; Argon used 147, 234 and 174. The visible answers were about the same length (task 1 produced two identical JSON blocks), so the gap is in the thinking: Flash thought far more before answering. Argon's price per token is 2.7 times higher, but it used about 5 times fewer output tokens, so its total came out lower.

That can change when Gemini API pricing changes. From 1 December 2026 Argon's price doubles, and the same token counts would cost about $0.0137, slightly more than Flash. Flash's price doubles from 1 January 2027.

The comparison code (Python)

This is the part of the script that calls the Gemini API and works out the cost, using httpx. Output tokens add candidatesTokenCount and thoughtsTokenCount, because both are billed. Grading works the same way as in the Haiku vs Sonnet test: parse the JSON and compare each field (task 1), take the last number on each table row (task 2), and count words and look for "10%", the hotline and any dates (task 3).

import time, httpx

PRICES = {"gemini-3.8-flash": (0.75, 3.75), "gemini-4-argon": (2.00, 10.00)}  # USD per million tokens

def ask(model: str, prompt: str, api_key: str):
    started = time.monotonic()
    reply = httpx.post(
        f"https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent",
        headers={"x-goog-api-key": api_key},
        json={"contents": [{"role": "user", "parts": [{"text": prompt}]}]},
        timeout=600,
    ).json()
    parts = reply["candidates"][0]["content"]["parts"]
    text = "".join(p.get("text", "") for p in parts if not p.get("thought"))
    used = reply["usageMetadata"]
    tokens_out = used.get("candidatesTokenCount", 0) + used.get("thoughtsTokenCount", 0)
    price_in, price_out = PRICES[model]
    cost = used["promptTokenCount"] * price_in / 1e6 + tokens_out * price_out / 1e6
    return text, time.monotonic() - started, cost

Limits of this test

• Each task ran once. Thinking token counts can vary a lot between runs, and so can cost and time.
• All short tasks with clear answers. Long, multi-step work, coding and large documents, where Google says Argon is strongest, were not tested.
• Prices are introductory and will change: Argon doubles from 1 December 2026, Flash from 1 January 2027.

Takeaway: don't pick a model by price per token

1. Measure real cost on your own tasks. As the Gemini 4 Argon vs Flash numbers show, price per token is only half the story; a model that thinks less can cost less despite a higher rate.
2. Check strict requirements with code (word counts, format, what the last line must be). Argon going over 120 words is exactly the kind of slip a quick read misses.
3. Re-run when prices change. With the API, switching models is a one-line change to model, so re-run your own test set whenever the price list moves.

Frequently asked questions

How much does Gemini 4 Argon cost on the API?

According to the Gemini API pricing page updated on 13 October 2026 (paid tier), Argon costs $2 per million input tokens and $10 per million output tokens (thinking included), an introductory price until 30 November 2026. From 1 December 2026 it is $4 and $20. Argon is not on the free tier.

Is Gemini 4 Argon better than Gemini 3.8 Flash?

On the three short office tasks in this test, Flash got 15/15 items right and Argon 14/15, because its email went over the 120-word limit. Argon was faster and cheaper in this run. Long, multi-step work and coding were not tested.

Why did Argon cost less than Flash despite its higher price?

Thinking tokens are billed as output. In this run Flash used 2,912 output tokens across the three tasks and Argon only 555, so even at 2.7 times the price per token Argon's total was lower ($0.00687 against $0.01135).

Will Gemini 4 Argon stay cheaper than Flash?

Not necessarily. Argon's price doubles on 1 December 2026, and the same token counts would then cost about $0.0137, slightly more than Flash. Flash's price doubles from 1 January 2027.

Is Gemini 3.8 Flash available on the free tier?

Yes. The Gemini API pricing page lists a free tier for Gemini 3.8 Flash, while Gemini 4 Argon is not available on the Free tier or on the Google AI Pro plan.

How can I compare two models myself?

Prepare a few tasks with known answers, send the same prompt to each model through the API, and let code compare the replies with the answers. Take token counts from the usageMetadata the API returns, remember to add thinking tokens, and work out cost from the price list.