Free, self-hosted AI model router. OpenRouter / ClawRouter alternative using your own API keys. 14-dimension classifier routes to the right model (Anthropic/OpenAI/Kimi) automatically. No middleman, no markup. Built for OpenClaw.

Complete list of AI models available via EvoLink API, with ready-to-use OpenClaw configurations

A collection of recipes/notebooks showcasing use-cases of open-source models with Qubrid AI.

Point your existing SDK at one URL and reach every LLM vendor — with real failover, not a try/except. One static Rust binary.

OpenAI-compatible API CLI for DeepSeek V3, DeepSeek R1, and Qwen 3.5. Agent-friendly — every command emits --json with stable exit codes.

Never hit a rate-limit again. Route Claude Code, Cursor & 40+ providers through the subscription you already pay for, cut 40-80% tokens (RTK), stay un-banned. Self-hosted LiteLLM / OpenRouter / 9router alternative — one Go binary, anti-ban + sovereign P2P mesh.

Migration guides, rollout checklists, cost-control patterns, and LLM routing recipes for OpenAI-compatible APIs. Covers OpenRouter alternatives, failover strategies, and production deployment.

Open-source proof that token998.com does not swap models or harvest prompts.

Code examples for SoxAI — unified AI API gateway for 200+ models

Storefront for unorouter.ai. Next.js 16, React 19, Tailwind v4 frontend for browsing and purchasing AI model access.

Official Python client for Inference Labs - vendor-neutral router for the major cloud LLMs.

Official JavaScript/TypeScript client for Inference Labs - vendor-neutral router for the major cloud LLMs.

SoxAI Go SDK — Access 200+ AI models through one OpenAI-compatible API

Practical checklist, regression matrix, and test suite for safely switching LLM providers. Covers prompt compatibility, token counting, streaming differences, and rollback strategies.

SoxAI Python SDK — Access 200+ AI models through one OpenAI-compatible API

SoxAI Node.js/TypeScript SDK — Access 200+ AI models through one OpenAI-compatible API

A VS Code extension providing direct access to multiple LLM providers with composite model failover & load-balancing, analytics, and cost control — self-contained, no external router service required.