Gemini 4 Argon

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents.

MultimodalThinkingToolsFiles1M Context

Context Window

1M tokens

gemini-4-argon

Max Output

1M tokens

Input

$1.8$2.00

10% off

1M tokens

Output

$9$10.00

10% off

1M tokens

Model Codegemini-4-argon

Playground

Model Code

gemini-4-argon

Reference inputs

Reference Images0/10

Click or drag

Enter your prompt here...

Output

No output yet

Pricing

Plan	Context Window	Max Output	Input	Output	Cache Write	Cache Read
gemini-4-argon	1M tokens	-	$1.8$2.0010% off 1M tokens	$9$10.0010% off 1M tokens	-	-

Context caching · $0.09 · 1M tokens

README

Gemini 4 Argon is Google's flagship reasoning model, designed for complex software engineering, deep math and science, and long-horizon autonomous agents. It pairs deep reasoning with multimodal input (text, image, audio, video, PDF) and text output, served over the Gemini native protocol.

Gemini 4 Argon is a reasoning model: it can spend substantial tokens on thinking before producing the answer, so max_tokens should be set well above the expected answer length.
It supports multimodal input (text, image, audio, video, PDF) with text output, tool use, and file handling over a 1M-token context window.
It targets complex software engineering, deep math and science, and long-horizon autonomous agent workflows, where its reasoning depth and 1M-token context are most valuable.

API

Use the API docs for request format, parameters, and integration details.

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents.

Model Code

gemini-4-argon

View API Docs

API

Endpoint

POST /v1beta/models/{model}:generateContent

Authentication

x-goog-api-key: YOUR_REACH_API_KEY
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1beta/models/YOUR_MODEL_ID:generateContent" \
  -H "x-goog-api-key: YOUR_REACH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Introduce ReachAPI in one sentence."
          }
        ]
      }
    ],
    "generationConfig": {
      "temperature": 0.2
    }
  }'

Related Models

Other models from the same vendor

Gemini 4 Argon

Playground

Pricing

README

API

Related Models

Gemini 3.8 Flash

Gemini 3.7 Flash

Gemini 3.6 Flash

Gemini 3.1 Flash Image Preview

Gemini 3.1 Flash Lite

Gemini 3.1 Pro Preview