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

# Gemini 4 Neon

> Multimodal reasoning for coding, document analysis, and multi-step tool use.

Gemini 4 Neon supports text generation and image, audio, video, and document understanding through Chat Completions and Responses.

Reasoning defaults to `high`. Use `low`, `medium`, `high`, or `xhigh`; `minimal` and thinking budgets are not supported.

The default output budget is 65,536 tokens. Set a larger budget for automatic continuation within the shared 1,048,576-token input and output window. Reasoning and tool calls count toward output.

Preserve all returned `providerMetadata.google.parts` across turns. Only the first function call in a parallel turn carries a thought signature. Return tool results in call order and end history with a user message or completed tool results.

For applications that compact or edit earlier history, set `providerOptions.google.generationConfig.thinkingConfig.prefixMismatchBehavior` to `DROP`; the default is `ERROR`.

Custom temperature, top\_p, and top\_k values are ignored. Frequency and presence penalties and multiple candidates are not supported. Implicit caching starts at 4,096 tokens; explicit caching is not supported.

Office and OpenDocument files can be supplied as Base64 data URLs with their correct MIME type through file content parts, including tool results.

Enable Google Search or URL Context through providerOptions.google.tools. Search is charged per actual query; search-result input tokens are free. Use Search separately from other built-in tools and Agentic video.

Video content parts accept mediaProcessing: STATIC (default) or AGENTIC. Count input tokens without a wallet charge through POST /v1/token-counts.

## Model ID

```text theme={"dark"}
gemini-4-neon
```

Pass this exact public ID in the top-level `model` field.

## Supported modes

* `chat_completions`
* `responses_api`
* `visual_understanding`
* `text_generation`

## Inputs

* `Text`
* `Image`
* `Video`
* `Audio`

## Outputs

* `Text`

## Capabilities

* Not specified

### Additional capabilities

* `Chat completions`
* `Function calling`
* `Code execution`
* `Computer use`
* `Responses API`
* `Video understanding`
* `SSE streaming`
* `Multimodal understanding`
* `Reasoning`
* `Structured output`
* `Google Search grounding`
* `URL Context`
* `Agentic video understanding`
* `Token counting`
  See [Function calling](https://docs.gengen.farm/tool-calling.md) for tool declarations and result submission.

See [Gemini tools](https://docs.gengen.farm/api-reference/google/tools.md) for built-in tools, conversation replay, and streaming requirements.

## Technical details

| Property | Value |
| - | - |
| Model family | `Google` |
| Modality | `reasoning` |
| Processing | `Synchronous response` |
| Endpoint | `/api/gengen/v1/chat/completions` |
| Context window | `1M tokens (input and output combined)` |
| Streaming | `Supported (Server-Sent Events)` |
| Max input tokens | `1,048,576 minus output tokens` |
| Max output tokens | `1,048,576 minus input tokens` |

> [!NOTE]
>
> Availability and final customer prices can change. Check the [Dashboard model catalog](https://gengen.farm/dashboard?section=models) before production use.

See the [API reference overview](https://docs.gengen.farm/api-reference/introduction.md) for authentication, request conventions, and response schemas.


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