Google AI Studio

Google AI Studio is Google's official developer platform for Gemini, with generous free API quotas for flagship multimodal and coding models such as Gemini 3.8 Flash and Gemini 3.7 Flash. Create an API key in seconds without a credit card; endpoints are natively OpenAI-compatible.

Showing 4 of 4 active models
Google AI Studio

Gemini 3.7 Flash

Official Google AI Studio Gemini 3.7 Flash API with hybrid thinking, 2M context, and generous daily free quotas.

text-generation, image-understanding
rate limit
Google AI Studio

Gemini 3.8 Flash

Official Google AI Studio Gemini 3.8 Flash API with 15 RPM / 1500 RPD free tier, 1M context, and OpenAI SDK compatibility.

text-generation, code-generation, image-understanding, speech-to-text
rate limit
Google AI Studio

Gemini 2.5 Flash-Lite

Free via Google AI Studio: roughly 1,000 requests/day — the highest free quota — rate-limited, no credit card. Daily quota resets at midnight Pacific.

text-generation, image-understanding
rate limit
Google AI Studio

Gemini 2.5 Flash

Free via Google AI Studio: roughly 250 requests/day, rate-limited, no credit card required. Daily quota resets at midnight Pacific. Google AI Pro adds $10/mo Cloud credit for more.

text-generation, image-understanding
rate limit

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Frequently Asked Questions about Google AI Studio

Community Feedback

Comments are tied to your GitHub account — sign in to join the discussion.

Explore Other Free AI Providers

Command Code GOAT
Command Code GOAT 是专为全栈与高频开发者打造的高杠杆订阅计划。每月仅需 $10 即可获得 $70 算力额度（7倍杠杆），全量解锁涵盖 30+ 款开源及闭源模型，并开放支持 OpenAI 与 Anthropic 双协议的标准 Provider API，可直接将 API Key 接入 Cursor、Claude Code、Codex、ZCode 与 Pi。
Command Code
Command Code 是专为开源模型（DeepSeek、Qwen、MiniMax 等）打造的终端 Coding Agent 外骨骼。独创 taste-1 神经符号自适应引擎，可从开发者的编辑与接受行为中自动学习代码偏好，并针对开源模型的 Tool-call 与 Token 消耗进行深层优化与中间层缓存。
Vultr
Vultr 是全球顶尖的独立云基础设施服务商，提供高性能 Cloud GPU 与原生兼容 OpenAI 接口标准的 Serverless Inference 无服务器推理平台。新用户通过专属推荐可获 $300 试用额度（30天有效），支持免部署零门槛直调 DeepSeek V4.1 Flash、Qwen 3.8 等前沿大模型。
AMD Radeon Cloud
AMD 官方面向开发者推出的 Radeon Cloud Token Factory 算力平台，提供开箱即用的免配置 AI 模型 API（涵盖 DeepSeek V4 Flash 1M、DeepSeek V4 Flash Vision、Qwen 3.8 Flash、MiniCPM 5 1B 等 4 大旗舰模型），原生兼容 OpenAI 与 Anthropic 双协议。
NVIDIA NIM
NVIDIA NIM (Inference Microservices) provides optimized cloud and self-hosted API endpoints for enterprise and open-source models with 1,000 free inference credits on registration.
Zhipu AI
智谱 AI 开放平台（BigModel），提供 GLM-5.3-Flash、GLM-4 等全系列前沿大模型与 GLM Coding Plan 开发者订阅。