> ## 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 2.5 Flash

> Kyma's best long-context value pick with 1M context and multimodal input support.

## Overview

`gemini-2.5-flash` is the best choice when context length is the main constraint. It gives you 1M context and multimodal input without going to a premium flagship route.

## Specs

| Field              | Value                                              |
| ------------------ | -------------------------------------------------- |
| Model ID           | `gemini-2.5-flash`                                 |
| Best for           | Long context, fast throughput, 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          | Cheap                                              |
| Release stage      | Stable                                             |

## Use this when

* You need extremely long context.
* You want a cheap long-context model for analysis or extraction.
* You need multimodal input across more than just images.

## Pick something else when

* You want the best default quality: use [`qwen-3.6-plus`](/models/qwen-3.6-plus).
* You need stronger agentic coding behavior: use [`kimi-k2.6`](/models/kimi-k2.6).
* You need deeper reasoning than throughput: use [`deepseek-r1`](/models/deepseek-r1).

## 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-2.5-flash",
    messages=[{"role": "user", "content": "Summarize this long document set and extract the key decisions."}]
)
```