​

Custom Provider

Connect any OpenAI-compatible API as a custom provider.

​

Setup

1. In Pawz → Settings → Providers → Add Provider → Custom
2. Enter:
   • Base URL — the API endpoint (must be OpenAI-compatible)
   • API key — if required
   • Default model — the model name to use

​

Configuration

​

Compatible services

Any service that implements the OpenAI chat completions API:

• LM Studio — http://localhost:1234/v1
• text-generation-webui — http://localhost:5000/v1
• vLLM — http://localhost:8000/v1
• LocalAI — http://localhost:8080/v1
• Together AI — https://api.together.xyz/v1
• Fireworks AI — https://api.fireworks.ai/inference/v1
• Perplexity — https://api.perplexity.ai
• Groq — https://api.groq.com/openai/v1

​

Requirements

The API must support:

• POST /chat/completions endpoint
• Streaming via stream: true
• Tool/function calling (for agent tools to work)

​

Tips

• Test with a simple chat message first to confirm connectivity
• If tools don’t work, the API may not support function calling — the agent will still work for conversation
• You can add multiple custom providers pointing to different services