API Keys Setup Guide

Beginner · 20–30 min · Google account; Cherry Studio for configuration

Models are the engines. API keys are the ignition switches that let you choose which to start.

Overview

This guide helps you set up and manage API keys for AI models and services. You need them to access the tools used in the Research Memex workflow.

Benefits:

• Access to AI models for different tasks
• Free tier options for testing and development
• Redundancy across providers for reliability
• Cost-effective access through multiple free tiers

Required setup:

• Google AI Studio (Primary - Required)
• OpenRouter (Recommended for model testing)

Optional providers:

• Anthropic Claude (via API)
• OpenAI GPT models
• Other specialized providers

Provider setup

Subscriptions you already hold

A subscription is often the cheapest model access a participant has. A ChatGPT plan includes Codex, and its lighter models stretch the usage limits further; the Codex app also accepts other providers through its configuration, so one OpenRouter key can serve it too. Read the current limits on the vendor's pricing page rather than assuming any tier is unlimited: none is.

One local endpoint for all of them (advanced)

CLIProxyAPI wraps the logins behind Antigravity, Codex, Claude Code, Grok Build, and Kimi into one local server that speaks the OpenAI, Gemini, and Claude API shapes. Clients see a single base URL, http://127.0.0.1:8317 by default, and a single key, so a Cherry Studio, Codex, or Claude Code session can reach any subscription-backed model without a provider key per app. It is how the author runs Kimi and Grok inside the Codex app.

# macOS, via Homebrew
brew install cliproxyapi
brew services start cliproxyapi

Other platforms use the project's installer or its desktop client, EasyCLI; the project documentation has the client configuration for each app. Two cautions. Setting it up is fiddly, which makes it a good first job for the agent itself. And the project's documentation carries no statement about the providers' terms of service; whether routing a consumer subscription through an API is allowed is each provider's call, so read the terms of the subscription before building a course on it.

Testing your setup

Most platforms include built-in testing tools:

Cherry Studio:

• Select several models in the input area, or mention them with the @ syntax (e.g., @gpt-5.5 @claude-sonnet-5 Compare these approaches...), and one message is answered side by side
• See Cherry Studio Setup Guide for detailed testing instructions

OpenRouter:

• Visit openrouter.ai/chat for web-based model testing
• Try free models without setup
• Compare responses across different providers
• OpenRouter charges a service fee when you buy credits.

Cost management

Free and paid tiers:

• Google AI Studio: Free tier with daily limits
• OpenRouter: Free models for testing, pay-as-you-go for extensive use (service fee applies)
• Other providers: Free and paid options available

Budget tips:

• Start with free tiers for testing
• Monitor usage in provider dashboards
• Use course-provided API budget for intensive work

Security best practices

API key storage:

• Use password managers or secure notes
• Never store in plain text or shared documents
• Cherry Studio stores your keys securely

Multiple providers:

• Set up Google AI Studio as primary (free)
• Use OpenRouter for testing different models
• Have backup providers ready

Quick reference

Provider comparison

Recommended configurations

For beginners:

1. Google AI Studio (primary)
2. OpenRouter (secondary)

For advanced users:

1. Google AI Studio (free work)
2. OpenRouter (model testing)
3. Additional providers as needed

For budget-conscious users:

1. Google AI Studio (free)
2. OpenRouter (cost-effective multi-model)

Cost estimates

Monthly budget examples:

• Light usage: $0-5 (Google AI Studio free)
• Moderate usage: $5-15 (OpenRouter + occasional paid)
• Heavy usage: $15-50 (Multiple providers)

Resources

• Google AI Studio Documentation
• OpenRouter Model Rankings
• Anthropic API Docs
• OpenAI API Reference