Custom Providers & API Keys

Add your own AI providers and API keys for unlimited usage.

Why Use Custom Providers?

• Unlimited Usage — No credit consumption when using your own API key
• More Models — Access any model not in the built-in list
• Custom Endpoints — Connect to self-hosted models or private APIs
• Direct Connection — Requests go straight to the provider, PandaNpc is just the interface

Adding a Custom Provider

1. Open Settings → Model Configuration
2. Click Add Provider
3. Fill in the provider details:

Field	Description	Example
Provider Name	Display name	My OpenAI
API Base URL	API endpoint	https://api.openai.com/v1
API Key	Your secret key	sk-...

4. Click Save

Adding Models to a Provider

After creating a provider:

1. Click Add Model under the provider
2. Fill in model details:

Field	Description	Example
Model Label	Display name	GPT-4o
Model Value	API model ID	gpt-4o-2024-08-06
Model Type	Category	openai

3. Click Save
4. The model now appears in your model selector

Compatible APIs

PandaNpc works with any API that follows the OpenAI chat completions format:

• OpenAI — api.openai.com
• Azure OpenAI — your-resource.openai.azure.com
• OpenRouter — openrouter.ai/api
• Together AI — api.together.xyz
• Groq — api.groq.com
• Ollama (local) — localhost:11434
• LM Studio (local) — localhost:1234
• Any OpenAI-compatible endpoint

Managing Models

• Enable/Disable — Toggle models on/off without deleting them
• Set Default — Choose which model is selected by default in new conversations
• Reorder — Drag models to arrange their order in the selector
• Delete — Remove models you no longer need

Troubleshooting

"Model not responding"

• Check that your API key is valid and has credits
• Verify the API base URL is correct (include /v1 for OpenAI)
• Ensure the model ID matches the provider's documentation

"Network error"

• Check your internet connection
• If using a local model (Ollama/LM Studio), ensure the server is running
• Check if a proxy/VPN is blocking the connection