# cheaper-inference/OmniRoute

> Gateway to 359 AI providers (150+ free) and 1200+ models through one OpenAI-compatible endpoint with quota-aware auto-fallback and token compression.

- Magnitude: 4.2 out of 10 — Steady
- Stars: 79,506 total · +67 stars measured 2026-10-22, 00:37–04:50 UTC, ≈ 414 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-02-13 · Last push: 2026-10-22
- GitHub: https://github.com/cheaper-inference/OmniRoute · Homepage: https://omniroute.online · Page: https://gitnova.dev/en/r/cheaper-inference/OmniRoute

## Useful for

- Connect Claude Code, Cursor or Cline to free models via a single endpoint
- Set up auto-fallback between providers when a quota runs out
- Cut token usage by 15-95% with built-in compression

## Why it’s here

- Star-counter measurements on 2026-10-22 (UTC), 00:37–04:50: 79439 → 79506 stars (+67). This is the change over that interval.
- Estimated end-of-day forecast: about +413 stars, using observed gains and the previous day.
- About 49 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 11,561
- Issues and pull requests: 17,246
- Watchers: 458
- Average over the last week: 425 per day
- Usual pace: 383 per day
- Stars in the last hour (measured): 16
- Latest release: v3.8.52 (2026-10-19)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-23 … 2026-10-22: 324, 318, 293, 295, 300, 318, 386, 341, 327, 311, 300, 366, 349, 345, 313, 389, 354, 305, 413, 432, 447, 464, 411, 352, 405, 425, 435, 478, 469, 67

## Magnitude by day, last 14 days

10-05 4.3, 10-06 4.1, 10-07 4.1, 10-08 4.2, 10-09 4.5, 10-10 4.2, 10-11 4.1, 10-12 4.4, 10-13 4.0, 10-18 4.3, 10-19 4.7, 10-20 4.6, 10-21 4.5, 10-22 4.2

## Similar by description

1. **decolua/9router** — 2.9 · Steady · AI agents · JavaScript · +9 stars measured 2026-10-22, 00:40–04:52 UTC, ≈ 56 by evening
   Local router for AI coding tools: connects Claude Code, Cursor, Cline and other CLIs to 40+ providers, auto-fallbacks between them, and compresses tool output to save tokens.
   Full card: https://gitnova.dev/en/r/decolua/9router.md
2. **maximhq/bifrost** — 2.2 · Steady · Language models · Go · +3 stars measured 2026-10-22, 00:41–04:54 UTC, ≈ 22 by evening
   High-performance Go AI gateway that unifies 23+ LLM providers (OpenAI, Anthropic, Bedrock, etc.) behind a single OpenAI-compatible API with fallbacks, load balancing, and semantic caching.
   Full card: https://gitnova.dev/en/r/maximhq/bifrost.md
3. **QuantumNous/new-api** — 3.0 · Steady · Language models · Go · +22 stars measured 2026-10-22, 00:05–04:51 UTC, ≈ 83 by evening
   Self-hosted AI gateway that aggregates multiple LLM providers behind a unified OpenAI-, Claude-, or Gemini-compatible API with routing, access, and cost management.
   Full card: https://gitnova.dev/en/r/QuantumNous/new-api.md
4. **Wei-Shaw/sub2api** — 3.1 · Steady · AI agents · Go · +24 stars measured 2026-10-22, 00:05–04:51 UTC, ≈ 95 by evening
   An API gateway for AI subscription services that unifies access to Claude, OpenAI, Gemini and Grok behind one interface and lets users share subscription quotas.
   Full card: https://gitnova.dev/en/r/Wei-Shaw/sub2api.md
5. **yetone/magpie** — 4.3 · Steady · AI agents · Go · +179 stars measured 2026-10-22, 00:38–04:50 UTC, ≈ 740 by evening
   A menu-bar utility for macOS/Linux/Windows that lets you pick the model for each AI agent (Codex, Claude Code, Gemini CLI, etc.) and runs a local gateway translating OpenAI and Anthropic APIs between agents and providers.
   Full card: https://gitnova.dev/en/r/yetone/magpie.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-22 05:00 UTC, updated every 30 minutes.