---
url: https://lettuceai.app/docs/api-keys
title: "API Keys — LettuceAI"
description: "How to get API keys from OpenAI, Anthropic, Google Gemini, DeepSeek, Groq, and 15+ other AI providers for LettuceAI."
---

Menu 

# API Keys

API keys sound scary. They are not. This page explains what they are, why LettuceAI uses them, and how to get one without overthinking it.

## What is an API key?

An API key is basically a **password that lets an app talk to an AI service**. LettuceAI itself does not run AI models, it connects you directly to a provider like OpenAI or Anthropic using your key.

You can think of LettuceAI as the interface, and the API key as the permission that tells the provider "this user is allowed to send requests."

## Why does LettuceAI use API keys?

-   You pay the provider directly, not LettuceAI
-   You choose which models and providers to use
-   You can switch or remove providers at any time
-   Your data stays under your control

## Do I need technical knowledge?

No. You don't need to code or understand APIs. You just copy a key once and paste it into LettuceAI.

## Will this cost money?

Most providers charge based on usage. For normal chatting, the cost is usually very small. You can always see usage and limits on the provider's dashboard.

## Are there free providers or free tiers?

Sometimes. Some providers offer free trial credits, free-rate limited access, or a small free tier for certain models.

But this changes often. A provider can change pricing, remove free access, add queues, or require billing setup at any time.

-   Some providers are completely paid from the start
-   Some offer temporary free credits for new accounts
-   Some offer limited free usage with slower speeds or strict caps

Do not assume a provider is free

Always check the provider's current pricing page or dashboard before using it heavily.

## Getting API keys for each provider

Below are short, provider-specific instructions. All of them follow the same idea: create an account, generate a key once, then paste it into LettuceAI.

### OpenAI

Best all-around models and strong reasoning.

1.  Go to [platform.openai.com](https://platform.openai.com)
2.  Log in or create an account
3.  Open **API Keys**
4.  Create a new secret key and copy it

### Anthropic (Claude)

Known for natural, careful responses and long conversations.

1.  Go to [console.anthropic.com](https://console.anthropic.com)
2.  Log in or sign up
3.  Open **API Keys**
4.  Create a new key

### Google Gemini

Fast models with good multimodal support.

1.  Go to [Google AI Studio](https://aistudio.google.com/app/apikey)
2.  Sign in with your Google account
3.  Click **Create API key**

### DeepSeek

Strong reasoning-focused and cost-efficient models.

1.  Go to [platform.deepseek.com](https://platform.deepseek.com)
2.  Create or log into your account
3.  Open the API or developer section
4.  Create and copy your API key

### Mistral AI

High-quality European models and open-model options.

1.  Go to [console.mistral.ai](https://console.mistral.ai)
2.  Sign in or create an account
3.  Open **API Keys**
4.  Create a new key

### Groq

Extremely fast responses using LPU hardware.

1.  Go to [console.groq.com](https://console.groq.com)
2.  Sign in
3.  Open the API section
4.  Generate an API key

### xAI (Grok)

Grok models with a more opinionated, conversational style.

1.  Go to [docs.x.ai](https://docs.x.ai)
2.  Follow the link to the xAI console
3.  Create an API key from your dashboard

### OpenRouter

One API key that gives access to many different models.

1.  Go to [openrouter.ai](https://openrouter.ai)
2.  Create an account or log in
3.  Open **Keys** in your dashboard
4.  Create a new API key

### Moonshot (Kimi)

Very long-context models, popular for large documents.

1.  Go to [platform.moonshot.cn](https://platform.moonshot.cn)
2.  Create an account
3.  Open the API management section
4.  Create and copy your API key

### Qwen (Alibaba DashScope)

Alibaba's Qwen models with strong multilingual support.

1.  Go to [DashScope Console](https://dashscope.aliyun.com)
2.  Log in with your Alibaba Cloud account
3.  Create an API key in the console

### Anannas AI

Lower-cost access to multiple models.

1.  Go to [anannas.ai](https://anannas.ai)
2.  Create an account
3.  Open your dashboard
4.  Generate an API key

### zAI (GLM)

Access to GLM models through Zhipu AI's coding-focused API.

1.  Go to [z.ai](https://z.ai)
2.  Create or log into your account
3.  Generate an API key from settings

### NVIDIA NIM

NVIDIA-hosted inference for open and proprietary models.

1.  Go to [build.nvidia.com](https://build.nvidia.com)
2.  Sign in with an NVIDIA developer account
3.  Open API Keys and generate a new key

### Chutes

Decentralized compute marketplace for running open models.

1.  Go to [chutes.ai](https://chutes.ai)
2.  Create an account
3.  Open API settings and generate a key

### Featherless

Lightweight model hosting and inference.

1.  Go to [featherless.ai](https://featherless.ai)
2.  Create an account
3.  Open API or developer settings
4.  Create an API key

### NanoGPT

Simple pay-per-token API with minimal setup.

1.  Go to [nano-gpt.com](https://nano-gpt.com)
2.  Create an account
3.  Open your dashboard
4.  Generate an API key

## Adding your key to LettuceAI

1.  Open LettuceAI
2.  Go to **Settings → Providers**
3.  Click **Add Provider** or the **\+ icon** in the top right corner of the screen.
4.  Select the provider you created a key for
5.  Paste your API key
6.  Write a title for your provider
7.  Save

Security

Your API keys are stored locally on your device and sent directly to the provider.

## If something breaks

-   Check your provider balance or usage limits
-   If a key leaks, revoke it on the provider website
-   You can remove or replace keys anytime

[

PreviousAI Basics

](/docs/ai-basics)[

NextProviders

](/docs/providers)