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

# Gemini 3.5 Flash

> Call Google Gemini 3.5 Flash via Gemini API. The most intelligent Flash model, optimized for agentic and coding tasks.

Gemini 3.5 Flash is Google's most intelligent Flash model, available through Starrise AI via the native Gemini API. It delivers frontier performance in agentic execution, coding, and long-running tasks.

## Key Capabilities

* **1M token context window** — Handles massive documents and conversations, up to 65,000 output tokens
* **Thinking levels** — Control reasoning depth via `minimal`, `low`, `medium` (default), and `high`
* **Thinking persistence** — Model automatically retains intermediate reasoning across multi-turn conversations
* **Agentic execution** — Optimized for multi-agent deployments, problem solving, and large-scale agentic loops
* **Coding** — Excels at iterative coding cycles, rapid exploration, and prototyping
* **Production-ready** — Stable model, suitable for large-scale production use

## Quick Example

<CodeGroup>
  ```bash cURL theme={null}
  curl "https://ai.alad.com/v1beta/models/gemini-3.5-flash:generateContent?key=YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "contents": [
        {
          "role": "user",
          "parts": [{ "text": "Explain how parallel agentic execution works in three sentences." }]
        }
      ],
      "generationConfig": {
        "thinkingConfig": {
          "thinkingLevel": "medium"
        }
      }
    }'
  ```

  ```python Python theme={null}
  import requests

  url = "https://ai.alad.com/v1beta/models/gemini-3.5-flash:generateContent"
  params = {"key": "YOUR_API_KEY"}
  data = {
      "contents": [
          {
              "role": "user",
              "parts": [{"text": "Explain how parallel agentic execution works in three sentences."}]
          }
      ],
      "generationConfig": {
          "thinkingConfig": {
              "thinkingLevel": "medium"
          }
      }
  }

  response = requests.post(url, params=params, json=data)
  result = response.json()
  print(result["candidates"][0]["content"]["parts"][0]["text"])
  ```
</CodeGroup>

## Parameters

| Parameter                                       | Type   | Required | Description                                                             |
| ----------------------------------------------- | ------ | -------- | ----------------------------------------------------------------------- |
| `key`                                           | string | Yes      | API key (query parameter)                                               |
| `contents`                                      | array  | Yes      | Array of `{ role, parts }` objects                                      |
| `systemInstruction`                             | object | No       | System instruction with `parts` array                                   |
| `generationConfig.thinkingConfig.thinkingLevel` | string | No       | `minimal`, `low`, `medium` (default), `high` — controls reasoning depth |
| `generationConfig.temperature`                  | float  | No       | `0`–`2`. Not recommended for Gemini 3.5 Flash                           |
| `generationConfig.topP`                         | float  | No       | Not recommended for Gemini 3.5 Flash                                    |

<Card title="API Reference" icon="code" href="/en/api-reference/model-api/google/gemini-3.5-flash">
  View the interactive API Playground for Gemini 3.5 Flash.
</Card>