Gemini 4 Argon

Gemini 4 Argon is Google's next-generation frontier multimodal model designed for deep reasoning and general intelligence. Engineered for complex agent workflows requiring long-horizon planning, advanced mathematical and algorithmic logic, and long-range cross-modal context, it natively supports ultra-long context windows. It natively covers text, ultra-high-resolution images, long videos, high-fidelity audio, and complex technical documents. Featuring state-of-the-art multi-step tool use, rigorous causal reasoning, and native cross-modal generation/alignment, it is ideal for high-precision enterprise core services and frontier research scenarios.

Base URL

https://api.icreat.ai/v1

Model Code

gemini-4-argon

Authentication

All API requests must be authenticated using an API Key. You can retrieve your API Key in the console.

export ICREAT_API_KEY="your-api-key-here"

HTTP Request Headers

import os

API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + API_KEY,
}

Protect Your API Key Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

This model is accessed via an OpenAI-compatible Chat Completions interface and supports both streaming and non-streaming modes. When stream in the request body is set to false (default), the server returns the complete JSON response at once; when set to true, content is pushed in chunks via Server-Sent Events (SSE), making it ideal for real-time streaming displays.

POST/chat/completions

curl --fail-with-body --connect-timeout 10 --max-time 120 \
  -X POST https://api.icreat.ai/v1/chat/completions \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "video_url",
          "video_url": {
            "url": "https://example.com/example.mp4"
          }
        },
        {
          "type": "input_audio",
          "input_audio": {
            "data": "https://example.com/example.wav",
            "format": "wav"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/example.png"
          }
        },
        {
          "type": "text",
          "text": "Analyze the audiovisual and image materials above and provide a detailed reasoned response."
        }
      ]
    }
  ],
  "modalities": [
    "text"
  ]
}'

Request Parameters

The following parameters are accepted in the request body.

Total: 6 | Required: 2 | Optional: 4

modelstringrequired

The model ID used for completion. Must use the iCreat model_code (gemini-4-argon for this document, not the original provider model name).

Example: "gemini-4-argon"

messagesarray[object]required

A list of messages comprising the conversation.

max_tokensinteger

The maximum number of tokens to generate.

temperaturenumber

Sampling temperature, between 0 and 2.

streamboolean

If true, tokens are returned as Server-Sent Events (SSE).

thinkingobject

Extended deep reasoning/thinking mode configuration (controls thinking depth and token budget).

Response Parameters

The API returns responses compatible with the OpenAI Chat Completions format.

Total: 6

idstring

A unique identifier for the completion.

objectstring

The object type, always chat.completion.

createdinteger

The Unix timestamp when the completion was created.

modelstring

The model ID used for the completion.

choicesarray[object]

A list of completion choices.

usageobject

Token usage statistics.

LLM-Friendly Prompt

Below is an LLM-friendly Markdown prompt that you can copy into AI assistants such as Cursor or ChatGPT to help them understand how to integrate, call, and configure this model via the API. Click the "Copy LLM Prompt" button or the code block below to copy the full text.

# gemini-4-argon

> Gemini 4 Argon is Google's next-generation frontier multimodal model designed for deep reasoning and general intelligence.

## Overview

Perform chat completions and complex multimodal reasoning via the iCreat OpenAI-compatible Chat Completions API, supporting both streaming and non-streaming modes, native audiovisual input ingestion, and extended thinking mode.

## API Information

- **Base URL**: `https://api.icreat.ai/v1`
- **Endpoint (POST)**: `/chat/completions`
- **Model ID**: `gemini-4-argon`
- **Authentication**: `Authorization: Bearer ${ICREAT_API_KEY}`

## Calling Workflow

Single POST request; `stream: false` returns a full JSON payload, `stream: true` streams responses via SSE.

### Input Key Points

- `model` (Required): iCreat model_code `gemini-4-argon`
- `messages` (Required): Conversation message list supporting text, images (`image_url`), audio (`input_audio`), and video (`video_url`)
- Common Optional: `max_tokens` (max output tokens), `temperature` (sampling temperature), `stream` (streaming toggle), `thinking` (extended deep reasoning configuration)

### Output Key Points

- Retrieve the assistant response from `choices[0].message.content`

## Notes

- `model` must use the iCreat model_code (`gemini-4-argon`)
- All other fields follow the standard OpenAI Chat Completions protocol