MULTIMODAL / CHAT

Multimodal model playground

Explore Gemini 4 Argon with text, image, video, audio and PDF inputs in one chat. Calls use your account credits and settle against actual model usage.

Gemini 4 Argon

google/gemini-4-argon

What would you like to understand?

Ask a question, attach media, or combine them. Gemini 4 Argon accepts text, images, video, audio and PDF files and replies with text.

Max output

PNG, JPEG, WebP, MP4, MPEG, MOV, WebM, WAV, MP3, AIFF, AAC, OGG, FLAC, M4A and PDF · 4 MiB per file · 8 MiB total · 8 files per conversation

Model details

Gemini 4 Argon, served by Google · OpenRouter. Accepts text, images, video, audio and PDFs and returns text.

Text inputImage inputVideo inputAudio inputPDF inputText output

Model details →

Usage pricing

Input$5.72 / 1M

Cache read$0.29 / 1M

Output$28.58 / 1M

Credits use the undiscounted input/output/cache list prices ($4 / $20 / $0.20 per million tokens), with the same 30% margin rule. The current 50% OpenRouter promotion does not lower this credit rate.

Use the API

OpenAI-compatible chat completions endpoint. Authenticate with a Decisions API key and use multipart content for media.

POST /v1/chat/completions
Authorization: Bearer YOUR_API_KEY
{
  "model": "google/gemini-4-argon",
  "messages": [
    { "role": "user", "content": "Describe this clip." }
  ],
  "max_completion_tokens": 256
}

Manage API keys