Gemini 3.1 Pro Preview vs Gemini 4 Argon

As of October 21, 2026, Gemini 3.1 Pro Preview and Gemini 4 Argon cost the same per input token ($2.00 per 1M), but Gemini 3.1 Pro Preview costs 20% more per output token ($12.00 vs $10.00), and both have a 1M-token context window. Gemini 4 Argon's price is introductory through November 30, 2026.

Prices from LiteLLM's price fileChecked October 21, 2026

Gemini 3.1 Pro Preview vs Gemini 4 Argon side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of October 21, 2026.
	Gemini 3.1 Pro Preview	Gemini 4 Argon
Input, per 1M tokens	$2.00	$2.00
Output, per 1M tokens	$12.00	$10.00
Cache read, per 1M tokens	$0.20	$0.10
Cache write, per 1M tokens	–	–
Context window	1,048,576 tokens	1,048,576 tokens
Max output	65,536 tokens	1,048,576 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	4	3
Price shown is from	Google AI Studio	Google AI Studio, introductory until November 30, 2026
Added to LiteLLM	February 2026	October 13, 2026

Cheapest provider for each

Gemini 3.1 Pro Preview: Google AI Studio at $2.00 input and $12.00 output per 1M tokens (gemini/gemini-3.1-pro-preview)
Gemini 4 Argon: Google AI Studio at $2.00 input and $10.00 output per 1M tokens (gemini/gemini-4-argon)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of October 13, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	Gemini 3.1 Pro Preview	Gemini 4 Argon
Coding and agents
APEX-Agents	35.1%	82.4%
Reasoning and knowledge
GPQA Diamond	94.4% (high)	96.4% (high)
ARC-AGI-2	77.1%	91.3% (high)
SimpleQA Verified	73.5% (high)	76.0% (high)
Math
FrontierMath (tiers 1-3)	59.6%	86.0% (high)
FrontierMath (tier 4)	26.8%	78.0% (high)
OTIS Mock AIME 2024-2025	95.6%	100.0% (high)

When to pick which

Pick Gemini 4 Argon for

Costs 17% less per output token: $10.00 vs $12.00 per 1M.
Returns up to 1,048,576 tokens per response, vs 65,536.

From differences in the data above only; where the data is equal, no reason is given.

Call Gemini 3.1 Pro Preview or Gemini 4 Argon with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# Gemini 3.1 Pro Preview
response = completion(model="gemini/gemini-3.1-pro-preview", messages=messages)

# Gemini 4 Argon
response = completion(model="gemini/gemini-4-argon", messages=messages)

# Gemini 3.1 Pro Preview, falling back to Gemini 4 Argon if the call fails
response = completion(model="gemini/gemini-3.1-pro-preview", messages=messages, fallbacks=["gemini/gemini-4-argon"])

FAQ

Which is cheaper, Gemini 3.1 Pro Preview or Gemini 4 Argon?

Gemini 4 Argon is cheaper at 3 input tokens per output token: $4.00 per 1M tokens blended ($2.00 input, $10.00 output), versus $4.50 ($2.00 and $12.00) for Gemini 3.1 Pro Preview, as of October 21, 2026.

Which has the larger context window, Gemini 3.1 Pro Preview or Gemini 4 Argon?

Both have a 1,048,576-token context window.

Can I switch from Gemini 3.1 Pro Preview to Gemini 4 Argon without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "gemini/gemini-3.1-pro-preview" to "gemini/gemini-4-argon", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.