> ## Documentation Index
> Fetch the complete documentation index at: https://mixroute.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini 4 Argon

> Gemini 4 Argon: Google's reasoning model for complex coding, mathematics, science, and multi-step agents, with a shared 1M-token context window.

<link rel="alternate" hrefLang="en" href="https://mixroute.ai/docs/model-api/google/gemini-4-argon" />

<link rel="alternate" hrefLang="zh-Hans" href="https://mixroute.ai/docs/zh-hans/model-api/google/gemini-4-argon" />

<link rel="alternate" hrefLang="zh-Hant" href="https://mixroute.ai/docs/zh-hant/model-api/google/gemini-4-argon" />

<link rel="alternate" hrefLang="ja" href="https://mixroute.ai/docs/ja/model-api/google/gemini-4-argon" />

<link rel="alternate" hrefLang="x-default" href="https://mixroute.ai/docs/model-api/google/gemini-4-argon" />

[Gemini 4 Argon](https://ai.google.dev/gemini-api/docs/models/gemini-4-argon) is Google's flagship reasoning model for demanding software engineering, mathematical and scientific problem solving, and multi-step agents.

MixRoute lists `gemini-4-argon` with Gemini-native and OpenAI-compatible endpoint support.

## Model specifications

| Property | Description |
| - | - |
| Model ID | `gemini-4-argon` |
| Input | Text, images, video, audio, and PDF |
| Output | Text; no image or audio generation |
| Context window | 1,048,576 tokens shared across input, thinking, and output |
| Thinking levels | `low`, `medium` (default), and `high` |
| Model capabilities | Function calling and structured output |

## Quick examples

Set `MIXROUTE_API_KEY` to your MixRoute API key.

### Gemini native API

```bash theme={null}
curl "https://api.mixroute.ai/v1beta/models/gemini-4-argon:generateContent" \
  -H "Authorization: Bearer $MIXROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Explain how to safely retry a failed database transaction."
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 32768,
    "thinkingConfig": {
      "thinkingLevel": "medium"
    }
  }
}'
```

### OpenAI-compatible Chat Completions

```bash theme={null}
curl "https://api.mixroute.ai/v1/chat/completions" \
  -H "Authorization: Bearer $MIXROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "Explain how to safely retry a failed database transaction."
    }
  ],
  "max_tokens": 32768
}'
```

## Request parameters

### Gemini native API

| Parameter | Type | Required | Description |
| - | - | - | - |
| `contents` | array | Yes | Conversation content using `role` and `parts`. |
| `systemInstruction` | object | No | System instruction expressed as content parts. |
| `generationConfig.maxOutputTokens` | integer | No | Combined budget for thinking and generated text. The non-streaming example uses 32,768. |
| `generationConfig.thinkingConfig.thinkingLevel` | string | No | `low`, `medium`, or `high`; defaults to `medium`. |

### OpenAI-compatible Chat Completions

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model` | string | Yes | Use `gemini-4-argon`. |
| `messages` | array | Yes | Conversation messages. |
| `max_tokens` | integer | No | Generation-token budget; reserve room for reasoning as well as the answer. |
| `stream` | boolean | No | Set to `true` for SSE streaming. |

## Integration notes

* The [GenerateContent limits](https://ai.google.dev/gemini-api/docs/generate-content/long-decode) distinguish direct non-streaming REST calls (32,768 tokens per request) from streaming calls (65,536). These are provider limits; MixRoute route limits also apply.

* The 1M context window is not a 1M single-response allowance. Longer generation requires a continuation workflow; Google's OpenAI compatibility endpoint does not support long decode. This page covers standard MixRoute requests, not Interactions or continuation support.

* Use [thinking levels](https://ai.google.dev/gemini-api/docs/generate-content/thinking) instead of the deprecated `thinkingBudget`. Do not combine both. Native `thinkingLevel` does not accept `minimal`, and thinking cannot be disabled.

* Omit `temperature`, `topP`, and `topK` (`top_p` and `top_k` in snake\_case): Google ignores these sampling parameters for Argon. Explicit context caching via `cachedContent` is not supported.

* A small output budget can be consumed entirely by thinking, leaving a truncated or empty answer. Lower the thinking level to reduce reasoning effort rather than treating the token limit as an answer-length target.

Availability and pricing depend on your MixRoute route. See the [Model Marketplace](https://console.mixroute.ai/models).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.