Your own free AI key means unlimited Artie, at $0.

Option 1: Google Gemini (recommended)

Google AI Studio gives a free Gemini API key with no credit card. The free tier currently allows roughly 10 to 15 requests per minute and up to about 1,500 requests per day on the Flash models, which is far more than a day of career work. Exact limits live in Google's docs and change over time.

1. Go to aistudio.google.com/apikey and sign in with your Google account.
2. Click “Create API key”. Pick the default project Google offers, or create a new one.
3. Copy the key. It starts with “AIza”. Treat it like a password.
4. In Artispreneur, open Settings, Your AI keys, choose Google Gemini, paste the key, press Test, then Save.
5. Ask Artie anything. Your chats now run on Gemini Flash through your own key, with no daily cap.

One caution: on Google's unpaid tier, Google may use submitted content to improve its products. Do not paste sensitive contracts or private personal data into chats running on a free Google key. Rate limits: ai.google.dev/gemini-api/docs/rate-limits.

Option 2: OpenRouter (many free models, one key)

OpenRouter routes one key to dozens of models. Models whose names end in :free cost nothing, including strong open models from DeepSeek, Meta Llama and Qwen. Free usage is rate limited (about 50 free requests a day on a fresh account, more after a small one-time credit purchase, which is optional).

1. Go to openrouter.ai/keys and create an account (email or Google sign-in).
2. Click “Create Key”, name it “Artispreneur”, and copy it. It starts with “sk-or-”.
3. In Artispreneur, open Settings, Your AI keys, choose OpenRouter, paste the key, Test, then Save.
4. Artispreneur only routes OpenRouter chats to models on the free allowlist, so a free key never bills you.

Option 3: Ollama (free forever, runs on your computer)

Ollama runs open models locally, so there is no key and no per-message cost at all. Two honest caveats: local models are only reachable while your computer is on and reachable, and quality depends on your hardware. Ollama also offers a hosted cloud option if you prefer that.

1. Install Ollama from ollama.com/download (Mac, Windows or Linux).
2. Pull a model: run ollama pull llama3.1 for a balanced default, or ollama pull qwen3 for stronger reasoning. Smaller models like llama3.2 run on modest machines.
3. Ollama serves an OpenAI-compatible API at http://localhost:11434/v1 on your machine.
4. To use it with the hosted Artispreneur app, Artispreneur's servers need a reachable address for your Ollama: use Ollama Cloud, or expose your machine through a secure tunnel you control, then paste that base URL plus any key in Settings, Your AI keys under Ollama.
5. If you run Artispreneur tools locally instead, the default localhost address works as is.

Other providers that work here

Any provider with an OpenAI-compatible API can be added from the keys page. Your provider's terms, quota and any charges are between you and that provider.

How your key is handled

• Keys are encrypted with AES-256-GCM before they touch the database. The database never holds a readable key.
• After saving, a key is never shown again, not even to you. Only its last 4 characters display.
• Your key is only used for your own chats. If it fails, Artispreneur says so plainly and never silently switches you to a paid route.
• You can delete a key any time in Settings, and revoke it at the provider for a full cutoff.
• No key yet? The free plan still gives you 20 assistant messages a day on free models, no card required.