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

# Gemini 3 Flash

> A newer 1M-context Gemini option on Kyma for long-context reasoning and multimodal analysis.

## Overview

`gemini-3-flash` is the newer long-context Gemini option in Kyma. It is best treated as a newer, more premium long-context choice rather than the default safe pick.

## Specs

| Field              | Value                                       |
| ------------------ | ------------------------------------------- |
| Model ID           | `gemini-3-flash`                            |
| Best for           | Long-context reasoning, multimodal analysis |
| Context window     | 1M                                          |
| Max output tokens  | 8K                                          |
| Input modalities   | Text, image, audio, video                   |
| Output modalities  | Text                                        |
| Tool calling       | Yes                                         |
| Structured outputs | Yes                                         |
| Prompt caching     | Yes                                         |
| Speed              | Fast                                        |
| Cost band          | Premium                                     |
| Release stage      | Preview                                     |

## Use this when

* You want the newer Gemini generation.
* You need 1M context plus stronger reasoning than the cheaper long-context path.
* You can tolerate preview-stage behavior in exchange for newer capability.

## Pick something else when

* You want the safer long-context default: use `gemini-2.5-flash`.
* You want the best overall default: use [`qwen-3.6-plus`](/models/qwen-3.6-plus).
* You need the strongest coding agent behavior: use [`kimi-k2.6`](/models/kimi-k2.6).

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="gemini-3-flash",
    messages=[{"role": "user", "content": "Analyze this large mixed-media research dump and identify the strongest conclusions."}]
)
```