Summary

Free model router CLI addresses the challenge of discovering, benchmarking, and configuring free AI models for OpenCode and OpenClaw. It targets developers seeking efficient AI model integration, providing a streamlined workflow to identify and deploy optimal models with real-time performance metrics.

How It Works

The tool employs an interactive Text User Interface (TUI) that concurrently pings all registered AI models every two seconds, displaying live latency, uptime, and a verdict. Models are ranked by availability, SWE-bench capability tier, and latency. It integrates with NVIDIA NIM and OpenRouter, automating API key management and facilitating direct model selection for downstream tools like OpenCode.

Quick Start & Requirements

Installation is straightforward via package managers: npx @bytonylee/free-router, npm i -g @bytonylee/free-router, bunx @bytonylee/free-router, or bun install -g @bytonylee/free-router. Essential prerequisites include API keys for supported providers (NVIDIA NIM, OpenRouter), which can be configured via environment variables (NVIDIA_API_KEY, OPENROUTER_API_KEY) or a local JSON file (~/.free-router.json).

Highlighted Details

• Real-time TUI displaying live latency, uptime, and model verdicts.
• Automated configuration and launch of selected models directly into OpenCode.
• Non-interactive --best flag for scripting, outputting the optimal model ID.
• Interactive API key management with browser-based key acquisition assistance.
• Model ranking logic prioritizes availability, SWE-bench tier, and low latency.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or project roadmap were found in the provided README content.

Licensing & Compatibility

The project is released under the MIT License, which permits broad usage, including commercial applications and integration into closed-source projects.

Limitations & Caveats

The tool requires at least one API key to be configured for non-interactive --best mode functionality. While the README details fallback mechanisms for unsupported models, specific performance limitations or known bugs are not explicitly detailed.