> ## AI Agent Context > Get the complete documentation index at: https://aistudio.google.com/llms.txt > Use this file to discover all available pages. > For the full documentation in a single file, fetch: https://aistudio.google.com/llms-full.txt # Gemini 4 Argon Gemini 4 Argon (`gemini-4-argon`) is our efficient Gemini 4 frontier reasoning model. It delivers Gemini 4 intelligence with faster responses and lower token spend per turn compared to [Gemini 4 Carbon](/docs/models/gemini-4-carbon) across complex coding, agentic, math, and science tasks. Like Carbon, it supports a unified 1M-token context window and [long decode](/docs/long-decode) up to 1M tokens. {% button href="https://aistudio.google.com/prompts/new_chat?model=gemini-4-argon" variant="ais" %}Try in Google AI Studio{% /button %} ## Documentation {% id="documentation" %} Visit the [What's new in Gemini 4 Argon](/docs/whats-new-gemini-4-argon) page for full coverage of features, API changes, and how to choose between Argon and [Gemini 4 Carbon](/docs/whats-new-gemini-4-carbon). ## gemini-4-argon {% id="gemini-4-argon" %} {% table variant="model" %} * Property * Description --- * {% section class="model-property" %} {% icon name="id_card" /%}Model code {% /section %} * `gemini-4-argon` --- * {% section class="model-property" %} {% icon name="save" /%}Supported data types {% /section %} * **Inputs** Text, Image, Video, Audio, and PDF **Output** Text --- * {% section class="model-property" %} {% icon name="token_auto" /%}Token limits{% sup %}[[*]](/docs/tokens){% /sup %} {% /section %} * **Context window (unified input and output token limit)** 1,048,576 **Max output** 65,536 (default synchronous) / up to 1,048,576 (with [long decode](/docs/long-decode)) --- * {% section class="model-property" %} {% icon name="handyman" /%}Capabilities {% /section %} * {% section class="three-column-grid" %} {% section %} [**Agentic video understanding**](/docs/video-understanding#agentic-video-understanding) {% badge label=Supported (defaults to static) type="supported" /%} {% /section %} {% section %} [**Audio generation**](/docs/speech-generation) {% badge type="not-supported" /%} {% /section %} {% section %} [**Code execution**](/docs/code-execution) {% badge type="supported" /%} {% /section %} {% section %} [**Computer use**](/docs/computer-use) {% badge type="supported" /%} {% /section %} {% section %} [**Context caching**](/docs/caching) {% badge label=Supported (Implicit only) type="supported" /%} Note: Explicit caching is not supported. {% /section %} {% section %} [**File search**](/docs/file-search) {% badge type="supported" /%} {% /section %} {% section %} [**Function calling**](/docs/function-calling) {% badge type="supported" /%} {% /section %} {% section %} [**Grounding with Google Maps**](/docs/maps-grounding) {% badge type="supported" /%} {% /section %} {% section %} [**Grounding with Google Search**](/docs/google-search) {% badge type="supported" /%} {% /section %} {% section %} [**Image generation**](/docs/image-generation) {% badge type="not-supported" /%} {% /section %} {% section %} [**Live API**](/docs/live-api) {% badge type="not-supported" /%} {% /section %} {% section %} [**Structured outputs**](/docs/structured-output) {% badge type="supported" /%} {% /section %} {% section %} [**Thinking**](/docs/thinking) {% badge label=Supported (low, medium, high) type="supported" /%} {% /section %} {% section %} [**URL context**](/docs/url-context) {% badge type="supported" /%} {% /section %} {% /section %} --- * {% section class="model-property" %} {% icon name="speed" /%}Consumption options {% /section %} * {% section class="three-column-grid" %} {% section %} [**Batch API**](/docs/batch-api) {% badge type="supported" /%} {% /section %} {% section %} [**Flex inference**](/docs/flex-inference) {% badge type="supported" /%} {% /section %} {% section %} [**Priority inference**](/docs/priority-inference) {% badge type="supported" /%} {% /section %} {% /section %} --- * {% section class="model-property" %} {% icon name="123" /%}Versions {% /section %} * Read the [model version patterns](/docs/models#model-versions) for more details. * Stable: `gemini-4-argon` --- * {% section class="model-property" %} {% icon name="calendar_month" /%}Latest update {% /section %} * October 2026 --- * {% section class="model-property" %} {% icon name="id_card" /%}Model card {% /section %} * [Model card](https://deepmind.google/models/model-cards/gemini-4-argon/) --- * {% section class="model-property" %} {% icon name="paid" /%}Pricing {% /section %} * [Pricing](/docs/pricing#gemini-4-argon) {% /table %}