NewHow we catch a seller listing the wrong model, and refund you if one does.

Google: Gemini 4 Argon vs GPT-6 Luna

google/gemini-4-argon · openai/gpt-6-luna

As of November 20, 2026, GPT-6 Luna is the cheaper API on MartLLM: $0.0030 per million input tokens and $0.0149 per million output, versus $0.1798 / $0.8990 for Google: Gemini 4 Argon, about 98% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and MartLLM adds no fee. Choose GPT-6 Luna to cut cost; choose Google: Gemini 4 Argon when its capabilities fit your task better.

Google: Gemini 4 Argon vs GPT-6 Luna, side by side

SpecGoogle: Gemini 4 ArgonGPT-6 Luna
Price · input / 1M$0.1798$0.0030
Price · output / 1M$0.8990$0.0149
Context length1,048,5761,050,000
Max output tokens65,536128,000
Input modalitiestext, image, video, audio, filetext, image, file
Output modalitiestexttext
Tools / functionsYesYes
Vision (image input)YesYes
ReasoningYesYes
% off list91% off97% off
First token, median (7 days)9.4 s (10,457 requests)2.2 s (403 requests)

Best prices on MartLLM right now. No MartLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 20, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?

Google: Gemini 4 Argon vs GPT-6 Luna — FAQ

Is Google: Gemini 4 Argon or GPT-6 Luna cheaper?

GPT-6 Luna is cheaper on a blended token mix, by about 98%. A request costs what its provider charged, MartLLM adds no fee, and every request is listed with its cost in Activity.

What's the price difference between Google: Gemini 4 Argon and GPT-6 Luna?

Google: Gemini 4 Argon: $0.1798 in / $0.8990 out per 1M tokens. GPT-6 Luna: $0.0030 in / $0.0149 out per 1M tokens. That's roughly a 98% blended difference. Prices are live; MartLLM adds no fee.

Can I use both Google: Gemini 4 Argon and GPT-6 Luna with one API?

Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.martllm.com/v1 and your MartLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.martllm.com/v1/messages.

More comparisons