Configure AI Providers

1. Supported AI Providers

Neo AI supports 7 AI providers. You only need one to get started. Each offers different pricing, speed, and privacy trade-offs.

Tip for beginners: Start with Groq — generous free tier, fast inference, and the easiest to set up.

2. API Key Safety

⚠️ Important: When you switch between AI providers in the app, the API key field is cleared. This is by design — each provider uses a different key format and endpoint.

Before switching providers, always save your current API key in a secure text file. You will need to re-enter it if you switch back.

Best Practices

• Store keys in a password manager (1Password, Bitwarden, etc.)
• Never commit API keys to version control
• Never share your keys publicly
• Rotate keys periodically from the provider's dashboard

Getting Your API Key

All cloud providers follow the same basic flow:

1. Create an account on the provider's website
2. Navigate to API Keys (usually under Settings, Developers, or Account)
3. Generate a new API key — copy it immediately (you won't see it again)
4. Add credits/billing if required (most providers offer free tiers)
5. Paste the key into the AI Settings page in this app
6. Save your key in a secure text file before leaving the page

Security Note: Your API key is stored encrypted in your database. Never share it publicly or commit it to version control.

3. Provider Setup Instructions

3.1 OpenAI

1. Sign up at platform.openai.com
2. Go to API Keys → Create new secret key
3. Copy the key (starts with sk-...)
4. In the app Settings → AI Provider:
   • Provider: OpenAI
   • API Key: Paste your key
   • Base URL: https://api.openai.com/v1 (default)
   • Model: gpt-4o (recommended) or gpt-4o-mini

Example models: gpt-4o gpt-4o-mini gpt-4-turbo gpt-3.5-turbo

3.2 Anthropic

1. Sign up at console.anthropic.com
2. Go to API Keys → Create Key
3. Copy the key (starts with sk-ant-...)
4. In the app Settings → AI Provider:
   • Provider: Anthropic
   • API Key: Paste your key
   • Base URL: https://api.anthropic.com (default)
   • Model: claude-3-5-sonnet-20241022 (recommended)

Example models: claude-3-5-sonnet-20241022 claude-3-5-haiku-20241022 claude-3-opus-20240229

3.3 Groq

1. Sign up at console.groq.com
2. Go to API Keys → Create API Key
3. Copy the key (starts with gsk_...)
4. In the app Settings → AI Provider:
   • Provider: Groq
   • API Key: Paste your key
   • Base URL: https://api.groq.com/openai/v1 (default)
   • Model: llama-3.3-70b-versatile (recommended)

Example models: llama-3.3-70b-versatile deepseek-r1-distill-llama-70b llama-guard-3-8b

3.4 Gemini (Google)

1. Sign up at aistudio.google.com
2. Go to Get API Key → Create API Key
3. Copy the key
4. In the app Settings → AI Provider:
   • Provider: Gemini
   • API Key: Paste your key
   • Base URL: https://generativelanguage.googleapis.com/v1beta/openai/ (default)
   • Model: gemini-2.0-flash (recommended)

Example models: gemini-2.0-flash gemini-1.5-pro gemini-1.5-flash

3.5 OpenRouter

1. Sign up at openrouter.ai
2. Go to Keys → Create Key
3. Copy the key (starts with sk-or-...)
4. In the app Settings → AI Provider:
   • Provider: OpenRouter
   • API Key: Paste your key
   • Base URL: https://openrouter.ai/api/v1 (default)
   • Model: openai/gpt-4o or any supported model

Example models: openai/gpt-4o openai/gpt-oss-120b anthropic/claude-3.5-sonnet google/gemini-2.0-flash

OpenRouter gives you access to 200+ models through a single API. Browse available models at openrouter.ai/models.

3.6 DeepSeek

1. Sign up at platform.deepseek.com
2. Go to API Keys → Create API Key
3. Copy the key (starts with sk-...)
4. In the app Settings → AI Provider:
   • Provider: DeepSeek
   • API Key: Paste your key
   • Base URL: https://api.deepseek.com/v1 (default)
   • Model: deepseek-chat (recommended)

Example models: deepseek-chat deepseek-reasoner

4. Local LLM Setup (LM Studio & Ollama)

For air-gapped environments or complete data privacy, you can run LLMs locally on your machine. Neo AI supports two popular local LLM servers.

4.1 Option 1: LM Studio

LM Studio is a desktop app that lets you download and run LLMs locally.

Installation

1. Download from lmstudio.ai
2. Install and launch LM Studio
3. Download a model (e.g., Llama 3, Mistral, Phi-3) from the built-in model library

Start the Local Server

1. In LM Studio, go to the Local Server tab (left sidebar)

2. Select your downloaded model

3. Click Start Server

4. The server will run at http://localhost:1234 by default

Configure the App

In the app Settings → AI Provider:

• Provider: Local LLM
• API Key: Leave blank (local servers don't require auth)
• Base URL: http://localhost:1234/v1
• Model: Enter the exact model name shown in LM Studio (e.g., llama-3.2-3b-instruct)

Important: The app must be able to reach localhost:1234. If you're running the app in Docker, use host.docker.internal instead of localhost.

4.2 Option 2: Ollama

Ollama is a command-line tool for running LLMs locally.

Installation

macOS / Linux:

curl -fsSL https://ollama.com/install.sh | sh

Windows: Download from ollama.com and run the installer.

Pull and Run a Model

# Pull a model (e.g., Llama 3.2)
ollama pull llama3.2

# Run the model (starts server on port 11434)
ollama serve

Or run in background:

ollama serve &

Configure the App

In the app Settings → AI Provider:

• Provider: Local LLM
• API Key: Leave blank
• Base URL: http://localhost:11434/v1
• Model: llama3.2 (or whatever model you pulled)

Note: Ollama's OpenAI-compatible endpoint is at /v1, so the full URL is http://localhost:11434/v1.

4.3 Local LLM Requirements

4.4 Recommended Models for Local Use

5. Troubleshooting

"Connection failed" or "Cannot reach server"

• Ensure the local LLM server is running (localhost:1234 for LM Studio, localhost:11434 for Ollama)
• Check firewall settings
• If using Docker, use host.docker.internal instead of localhost

"Model not found"

• Verify the model name matches exactly (case-sensitive)
• In LM Studio: check the model name in the Local Server tab
• In Ollama: run ollama list to see installed models

Slow generation speed

• Use a smaller model (3B-7B parameters)
• Ensure you have enough RAM/VRAM
• Close other GPU-intensive applications
• For LM Studio: enable GPU acceleration in settings

API key errors

• Double-check the key is copied correctly (no extra spaces)
• Verify the key hasn't expired or been revoked
• Ensure billing is set up (for cloud providers)
• Check the provider's status page for outages

Need help? Check the other guides in the docs/ folder or contact support. 🚀