Gemini 3.5 Flash

Gemini 3.5 Flash is Google’s most intelligent Flash model, available through AnyFast via the native Gemini API. It delivers state-of-the-art performance for agentic execution, coding, and long-running tasks.

Google released gemini-3.5-flash as the GA model for Gemini 3.5 Flash on May 19, 2026. This is also the model behind gemini-flash-latest, and is suited for agentic execution, coding, and long-running tasks.

Key capabilities

1M token context window — Handle massive documents and conversations, with up to 65,000 output tokens
Thinking levels — Control reasoning depth with minimal, low, medium (default), and high
Thought preservation — Model automatically retains intermediate reasoning across multi-turn conversations
Agentic execution — Optimized for multi-agent deployment, problem-solving, and large-scale agentic loops
Coding — Excels at iterative coding cycles, rapid exploration, and prototyping
GA release — Stable model ready for production at scale

Quick example

curl "https://www.anyfast.ai/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"
      }
    }
  }'

import requests

url = "https://www.anyfast.ai/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"])

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

API Reference

View the interactive API playground for Gemini 3.5 Flash.

Getting started

Model Introduction

Resources

Gemini 3.5 Flash

Key capabilities

Quick example

Parameters

API Reference

​Key capabilities

​Quick example

​Parameters

API Reference

Key capabilities

Quick example

Parameters