Language model · from 3 credits
Write and analyze with Gemini 4 Argon
Gemini 4 Argon is Google's new model, released on October 13, 2026, and the first of the Gemini 4 family available on the Vercel AI Gateway. It is a reasoning model: it thinks before it writes, which makes it reliable on long instructions, documents to analyze and multi-step problems. On the canvas, it reads the text, images and PDFs connected to the Text node, with a one-million-token context. Its price puts it at the level of Claude Sonnet, above the Gemini Flash models.
What Gemini 4 Argon is
Gemini 4 Argon was released on October 13, 2026, the first model of the Gemini 4 family available on the Vercel AI Gateway. It is a multimodal reasoning model: it takes time to think before writing, reads text, images and PDFs, and accepts a one-million-token context. Google presents it as a model for document analysis and multi-step work.
Its price, two dollars per million input tokens and ten per million output, matches Claude Sonnet 5.5: above the Gemini Flash models, far below GPT-6 Astra. On Imaginode, each message is paid with your credits, and the price shows on the button before you send.
What it does on the canvas
In the Text node, Gemini 4 Argon receives an instruction plus the texts, images and PDFs you connect, and its answer feeds the nodes wired after it. It is at ease with a file to digest, a brand guide in PDF, a brief, a script, from which it draws a consistent series of image prompts or a video shot list.
Checked with a real request on October 15, 2026: it recognized a product photo and summarized an attached PDF. For a short question or a title to rephrase, Gemini 3.8 Flash stays faster and far cheaper; Argon takes the lead when the instruction gets long and every detail counts.
Gemini 4 Argon next to its closest siblings
Figures pulled from the same registry as billing: when a price or a cap changes, this table changes with it.
| Gemini 4 Argon | Claude Sonnet 5 | Claude Sonnet 5.5 | |
|---|---|---|---|
| Base price | 3 credit(s) / message | 3 credit(s) / message | 3 credit(s) / message |
How to use it on Imaginode
- 1Add a Text node and pick Gemini 4 Argon in the selector.
- 2Give your instruction; wire in other texts or images to analyze.
- 3The result feeds your connected Image and Video nodes directly.
Frequently asked questions
Can Gemini 4 Argon read PDFs?
Yes. Connect up to three PDF documents to the Text node: Gemini 4 Argon reads them with the instruction, and the price then follows the tokens actually used.
Do I need a Gemini subscription to use it?
No. On Imaginode, Gemini 4 Argon is paid per message with your credits, with no Google account and no API key, in the same canvas as image, video and voice.
How much does a message sent to Gemini 4 Argon cost?
Around 3 credit(s) per message, that is $0.04 (1 credit = $0.012). The cost shows before sending, with no separate subscription and no API key to manage: the same credits pay for all 126 models in the catalog.
Do I need a separate subscription to use Gemini 4 Argon?
No: Gemini 4 Argon is included in Imaginode, with no API key and no account with the provider. A single credit balance covers all 126 models, text, image, video and voice, and also powers the assistant that builds complete workflows.
Can I try Gemini 4 Argon for free?
Yes: signing up grants trial credits, no credit card required. Enough to test Gemini 4 Argon in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use Gemini 4 Argon?
No: Gemini 4 Argon runs server-side, in the browser, mobile included. Imaginode's node canvas wires its renders to the other models (references, camera, styles) with nothing to install.
Try Gemini 4 Argon on a real canvas
126 models, one account, credits that work everywhere. The price always shows before you generate.
Get started
GPT-5 (ChatGPT)