Skip to content
ShilpBot
AI Models

Google Gemini 4 Argon: Pricing, Specs and Limits

Google Gemini 4 Argon: flagship reasoning model, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs, limits and test prompts.

By ShilpBot Team · Published · 3 min read

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. The listing says Google trained it to keep context across long tasks.

It is the oldest of the three Gemini 4 models in this series (added 13 October 2026) and shares the Carbon price, so it has had the most time for real-world feedback.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

Google Gemini 4 Argon quick facts

DetailValue
DeveloperGoogle
Model IDgoogle/gemini-4-argon
Added to the catalogue2026-10-13
TypeFlagship reasoning model
ParametersNot listed
Context windowabout 1M tokens (1,048,576)
Maximum output943,718 tokens
Input typesaudio, file, image, text, video
Price2.00 in / 10.00 out per 1M tokens (cached input 0.10)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What Google Gemini 4 Argon is good for

  • Hard maths and science problems that need extended reasoning.
  • Autonomous multi-step agents that must keep context over long runs.
  • Complex software engineering across many files.

Limits of Google Gemini 4 Argon

  • Reasoning models can spend many output tokens thinking. Cap them.
  • It costs more than Hydrogen, so use it only where depth matters.
  • Verify mathematical answers independently.

How Google Gemini 4 Argon compares

  • Google Gemini 4 Carbon: Both have a 1,048,576-token context window; both cap output at 943,718 tokens; it costs 2.00 input and 10.00 output per million tokens against 2.00 and 10.00.
  • Google Gemini 4 Hydrogen: Both have a 1,048,576-token context window; both cap output at 943,718 tokens; it costs 2.00 input and 10.00 output per million tokens against 1.50 and 7.50.
  • NVIDIA Nemotron 3 Ultra: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 943,718 tokens against 65,536; it also accepts audio and file and image and video input; it is a paid model, while NVIDIA Nemotron 3 Ultra has a free listing.

Calling Google Gemini 4 Argon from code

Use the model ID google/gemini-4-argon with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "google/gemini-4-argon", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what Google Gemini 4 Argon can do

  1. Ask for a proof of a simple lemma and check each step.
  2. Give it a multi-file bug report and ask for a root-cause analysis before any fix.
  3. Compare reasoning effort settings on a logic puzzle.

What Google Gemini 4 Argon costs

The catalogue lists 2.00 per million input tokens and 10.00 per million output tokens, with cached input at 0.10 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 3.00. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.40 before caching. If your client reuses the same prompt prefix, cached input at 0.10 per million tokens can cut the input side of that bill by about 95 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

When should I choose Argon over Hydrogen?

Choose Argon for the hardest reasoning and long autonomous tasks. Choose Hydrogen for high-volume work where cost and speed matter more.

What are the cost and limits of Google Gemini 4 Argon?

As of 2026-11-16 the catalogue lists 2.00 per million input tokens and 10.00 per million output tokens. About 1M tokens (1,048,576) context window, up to 943,718 output tokens, model ID google/gemini-4-argon. Prices can change, so check the live model page.

#Google Gemini 4 Argon#Google model#AI model pricing#AI API pricing#AI chat model#reasoning model#OpenRouter