SKILL.md

Using gpt4free as an LLM Server for Bots (Clawbot/OpenClaw)

Overview

This skill covers running gpt4free as a local LLM server with an OpenAI-compatible REST API, custom model routing (config.yaml), and integration with bots like Clawbot or OpenClaw.

Best Practices

Start the API server with: python -m g4f --port 8080 (or use g4f api --debug --port 8080)
Use the /v1 endpoint for OpenAI-compatible requests (e.g., POST to http://localhost:8080/v1/chat/completions)
Define custom model routes in config.yaml to aggregate/fallback across providers
Place config.yaml in your cookies directory (e.g., ~/.g4f/cookies/config.yaml)
For Clawbot/OpenClaw, patch their config to point to your gpt4free server (see patch-openclaw.py)
Test with: g4f client "Hello" --model openclaw or Python client

Common Pitfalls

Not starting the server before connecting bots
Incorrect config.yaml path or syntax errors
Missing required Python dependencies (install with pip install -r requirements.txt)
Not exposing the correct port (default 8080)
Forgetting to patch bot configs to use your local endpoint

Workflow Steps

Install and set up gpt4free (see README)
Start the API server: python -m g4f --port 8080

(Optional) Create or edit config.yaml for custom model routing:

models:
    - name: "openclaw"
   	 providers:
   		 - provider: "GeminiCLI"
   			 model: "gemini-3-flash-preview"
   			 condition: "quota.models.gemini-3-flash-preview.remainingFraction > 0 and error_count < 3"
   		 - provider: "Antigravity"
   			 model: "gemini-3-flash"
   		 - provider: "PollinationsAI"
   			 model: "openai"

Patch your bot config (e.g., OpenClaw) to use http://localhost:8080/v1 as the base URL (see scripts/patch-openclaw.py)
Start your bot and verify it connects to gpt4free
Monitor logs and test with the Python client or CLI

2.1 KiB Raw Blame History