Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
A unified API gateway that routes requests to 70+ AI models from providers including OpenAI, Anthropic, Google, and others through a single API key. The endpoint is OpenAI-compatible, so existing OpenAI SDK code works by changing only the base URL and key. Billing and cost tracking are consolidated across all providers.
Replaces per-provider API keys and SDKs with one OpenAI-compatible endpoint, eliminating credential sprawl and fragmented billing across AI providers.
When to use it
- Switching between GPT-4 and Claude without changing application code
- Routing simple queries to cheap models and complex ones to GPT-4
- Comparing outputs from multiple models on the same prompt
- Analyzing images with vision models through a single shared endpoint
- Setting up automatic fallback when a primary model fails or is unavailable
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Compare how GPT-4.1, Claude-3-Sonnet, and Gemini-2.0-Flash each explain quantum computing
- 1Sends the same prompt to all three models via the unified /v1/chat/completions endpoint
- 2Receives each response with per-model latency and token cost in the usage field
- 3Formats responses side by side with cost and latency metadata
Three model responses with per-model token cost and latency shown together for comparison
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.