Google AI Studio

Verified ✅ Truly Free

Google AI Studio is Google's free prototyping console and API for Gemini models. The free tier covers Gemini 4 Hydrogen, the current Flash family (Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite), Gemini 3 Flash Preview and the Gemini 2.5 models; Gemini 4 Carbon and Argon and the newest Pro models are paid only. From December 1, 2026, requests to gemini-2.5-pro and gemini-2.5-flash are routed to newer models. Google no longer publishes the free per-model rate limits in its docs: they are shown in AI Studio.

Updated by the community — thanks, Anonymous (Jul 16, 2026) Suggest an edit

What changed:

Community Edit for Google AI Studio
Truly Free Community Pick Multimodal Fast Reliable Gemini 3.1
Get API Key Suggest Edit
4812

Overview

Provider Type

API

API Endpoint

https://generativelanguage.googleapis.com/v1beta

Free Tier Highlights

5-30 RPM (varies by model)

Why Choose Google AI Studio?

Google AI Studio is one of the most generous free LLM APIs: no credit card, Gemini 4 Hydrogen, the current Gemini Flash models (3.8 Flash, 3.6 Flash, Flash-Lite), Gemma 4 and the Gemini 2.5 models, with 1M-token context windows and image input.

Best for: almost everything, from chatbots to long-document work and coding agents. It is usually the first free key worth getting.

Watch out: Google no longer publishes the free per-model limits (they are shown inside AI Studio), Gemini 4 Carbon/Argon and the newest Pro models are paid only, and Gemini 2.5 requests are redirected to newer models from December 1, 2026.

Quick Start Guide

1

Sign in to Google AI Studio

2

Get API Key

3

Start Building

Available Models

10 free models
Model Name ID Context Capabilities
Gemini 3.8 Flash Free
gemini-3.8-flash
1 000 000 Context
-
Gemma 4 26B A4B IT Free
gemma-4-26b-a4b-it
256 000 Context
-
Gemma 4 31B IT Free
gemma-4-31b-it
256 000 Context
-
Gemini 3 Flash Preview Free
gemini-3-flash-preview
1 000 000 Context
-
Gemini 2.5 Flash-Lite Free
gemini-2.5-flash-lite
1 000 000 Context
-
Gemini 3.1 Flash-Lite Free
gemini-3.1-flash-lite
1 000 000 Context
-
Gemini 3.5 Flash-Lite Free
gemini-3.5-flash-lite
1 000 000 Context
-
Gemini 3.6 Flash Free
gemini-3.6-flash
1 000 000 Context
-
Gemini 4 Hydrogen Free
gemini-4-hydrogen
- -
Gemini 2.5 Flash Free
gemini-2.5-flash
1 000 000 Context
Thinking Multimodal

Integration Examples

Ready-to-use code snippets for your applications.

main.py
import requests
import os

# Get your API key from https://aistudio.google.com/
api_key = "YOUR_API_KEY"
url = f"https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash:generateContent?key={api_key}"

headers = {
    "Content-Type": "application/json"
}

data = {
    "contents": [{
        "parts": [{"text": "Explain how AI works"}]
    }]
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Free Tier Pricing & Limits

Rate Limit

Requests per minute

Varies by model (per-model limits are now shown only inside AI Studio)

Daily Quota

Requests per day

Varies by model. Free: Gemini 3.x Flash / Flash-Lite and Gemini 2.5 Pro/Flash (2.5 redirect to 3.x on Dec 12026); Gemini 3.x Pro and Gemini 4 are paid

Token Limit

Tokens per minute

1 000 000 Tokens per minute (Flash) / 2B Tokens per minute (3.1 Pro)

Monthly Quota

Per month limit

Free of charge

Use Cases

Content Generation

Data Extraction

Image & Video Analysis

Code Generation

chat bots

Limitations & Considerations

Data used for training (Unpaid tier)

Rate limits are enforced per minute/day

No SLA for free tier

Community Hub

Live

Join the discussion, share tips, and rate Google AI Studio.

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using Google AI Studio

Start Building Now