LiteLLM Gateway

SkillAI & models

Route LLM requests through a unified gateway supporting 100+ providers via LiteLLM at {{LITELLM_HOST}}:{{LITELLM_PORT}}.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the LiteLLM Gateway skill

What this skill tells your AI

The instructions your AI receives, as published by bidewio/better-openclaw in skills/litellm-gateway/SKILL.md and read by ahel’s review.

LiteLLM proxy is available at http://{{LITELLM_HOST}}:{{LITELLM_PORT}} within the Docker network, providing an OpenAI-compatible API for 100+ LLM providers.

Chat Completion

curl -X POST "http://{{LITELLM_HOST}}:{{LITELLM_PORT}}/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}'

List Available Models

curl "http://{{LITELLM_HOST}}:{{LITELLM_PORT}}/v1/models" \
  -H "Authorization: Bearer $LITELLM_API_KEY"

Tips for AI Agents

LiteLLM provides a unified OpenAI-compatible interface for all providers.
Use model aliases to switch providers without changing application code.
Supports load balancing, fallbacks, and spend tracking.

Signals

GitHub stars: 58
Forks: 6
Last commit: Aug 2026

Advanced

Item type: skill
Key: litellm-gateway
Source: github.com/bidewio/better-openclaw

github.com/bidewio/better-openclaw