[GitHub Trending] diegosouzapw/OmniRoute

7.5 relevance

Unified AI gateway with 352 providers is highly actionable for platform engineering and developer experience.

AI/ML github.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For a platform engineer or architect managing AI costs across multiple providers, OmniRoute eliminates the manual overhead of stacking free tiers and provides a single, audited dashboard to maximize token budgets without complex SDK integration.

Key Takeaways

Install OmniRoute with zero config via `curl http://localhost:20128/v1/chat/completions` and use the `/dashboard/free-tiers` endpoint to automatically route requests to the best available free provider pool, saving potentially millions of tokens monthly.

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cli...

Summary

OmniRoute is an open-source AI gateway that aggregates 444 free-tier entries across 34 provider pools to deliver approximately 1.47 billion free tokens per month, with quotas re-audited every two weeks. It supports 290+ providers and 1,185 unique chat model IDs as of v3.8.49, offering zero-config installation via a single cURL command and features like quota-aware scheduling, modality bridging (vision/audio/video), and a live free-tier dashboard. The project is backed by Kimi (Moonshot AI) and Cheaper Inference, with Kimi's API credits powering the AI-validated merge pipeline.

Author

diegosouzapw