gemini-4-argon — API, Pricing & Context Window | Vivgrid

gemini-4-argon is Google's flagship reasoning model in the Gemini 4 series, succeeding gemini-3.1-pro-preview for complex software engineering, deep mathematical and scientific problem solving, and long-horizon autonomous agents. It pairs a ~1.05M-token context window with up to ~1.05M max output tokens and accepts text, image, video, audio, and PDF inputs.

On Vivgrid, gemini-4-argon runs as a globally centralized model reachable through the same OpenAI-compatible endpoint and unified key as every other model in the catalog.

Specifications

Pricing

Pricing in USD per 1M tokens.

What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

Input is priced at $4.00 per 1M tokens, cached input at $0.20 per 1M tokens, and output (including thinking tokens) at $20.00 per 1M tokens, with a single flat rate across the full context window.

Use gemini-4-argon in your coding agent

gemini-4-argon works with the same Vivgrid key and https://api.vivgrid.com/v1 endpoint as every other model in the catalog. Grab your API key from the Vivgrid Console, then drop one of the configurations below into your agent of choice.

OpenCode

OpenCode has Vivgrid built in, so you can use gemini-4-argon without writing any config: open /models, search for vivgrid, paste your API key and pick the model. The OpenCode tutorial walks through it step by step.

Prefer to configure it by hand? Install OpenCode:

npm i -g opencode-ai

Declare gemini-4-argon under the Vivgrid provider in your global OpenCode config, ~/.config/opencode/opencode.json. The @ai-sdk/openai-compatible provider talks to Vivgrid over Chat Completions (/v1/chat/completions):

{
  "$schema": "https://opencode.ai/config.json",
  "model": "vivgrid/gemini-4-argon",
  "provider": {
    "vivgrid": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Vivgrid",
      "options": {
        "baseURL": "https://api.vivgrid.com/v1",
        "apiKey": "{env:VIVGRID_API_KEY}"
      },
      "models": {
        "gemini-4-argon": {
          "name": "gemini-4-argon",
          "tool_call": true,
          "attachment": true,
          "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] },
          "limit": { "context": 1048576, "output": 1048576 }
        }
      }
    }
  }
}

Export your key and launch OpenCode:

export VIVGRID_API_KEY="viv-xxxxxxxxxxxxx"
opencode

Use /models to switch between gemini-4-argon and other Vivgrid models mid-session. See the full OpenCode tutorial.

Pi

Install Pi:

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

Add gemini-4-argon to the Vivgrid provider in ~/.pi/agent/models.json. Pi talks to Vivgrid over Chat Completions (/v1/chat/completions):

{
  "providers": {
    "vivgrid": {
      "baseUrl": "https://api.vivgrid.com/v1",
      "apiKey": "viv-xxxxxxxxxxxxx",
      "api": "openai-completions",
      "models": [
        {
          "id": "gemini-4-argon",
          "input": ["text", "image"],
          "contextWindow": 1048576,
          "maxTokens": 1048576
        }
      ]
    }
  }
}

Make it the model Pi starts with in ~/.pi/agent/settings.json:

{
  "defaultProvider": "vivgrid",
  "defaultModel": "gemini-4-argon"
}

Then verify and start Pi:

pi --list-models vivgrid
pi

Or run a one-shot prompt without entering the TUI:

pi -p "explain the auth flow in this repo" --model vivgrid/gemini-4-argon

See the full Pi tutorial.

API surfaces

The Vivgrid Console catalogs gemini-4-argon on 2 surfaces, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

Quick start

Get an API key from the Vivgrid Console, then call gemini-4-argon directly.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-4-argon",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Choosing within the Gemini family

Prices are USD per 1M tokens at the base rate. Rows marked this page are the model described here.

Ideal use cases

• Complex software engineering and multi-step autonomous coding agents
• Deep mathematical, scientific, and cybersecurity reasoning
• Multimodal document, image, video, and audio synthesis up to ~1M tokens
• Long-horizon generation and analysis with up to ~1M output tokens

Related models

• gemini-3.1-pro-preview — the prior high-end Gemini release
• gemini-3.8-flash — faster, lower-cost Gemini sibling
• gpt-6-astra — OpenAI's frontier gpt-6 coding model