TokenFlux/TokenRouter

tokenrouter is the next generation llm gateway

What it solves

TokenRouter solves the complexity of managing multiple large language model (LLM) providers. Instead of integrating separate APIs for different vendors, it provides a unified gateway that allows users to access various models using a single API key.

How it works

It acts as a proxy layer between the user and multiple upstream AI platforms. It translates between different protocols (such as Anthropic Messages, OpenAI Chat Completions, and Gemini) and handles the routing of requests to the appropriate provider based on model availability, rate limits, or session stickiness. If an upstream provider fails, the system automatically switches to another available one.

Who it’s for

It is designed for developers and organizations that use a variety of AI models from different vendors and need a centralized way to manage access, monitor usage, and control costs.

Highlights

  • Multi-Provider Integration: Supports OpenAI, Anthropic, Gemini, Grok, DeepSeek, and others via API keys, OAuth, AWS Bedrock, and Vertex AI.
  • Protocol Conversion: Automatically converts requests between different vendor-specific protocols.
  • Access & Quota Management: Controls user/team quotas, concurrency, and RPM (requests per minute).
  • Billing & Payment: Built-in support for usage-based billing, subscriptions, and multiple payment gateways like Stripe, Alipay, and WeChat Pay.
  • Content Moderation: Intercepts requests based on keywords or hash rules and can automatically ban violating users.
  • Comprehensive API Support: Beyond text, it provides endpoints for embeddings, image generation/editing, video, speech (TTS/STT), and web search.

Related

  • Project
    QuantumNous/new-api

    New API is an open‑source, self‑hosted gateway that unifies access to many LLM providers behind a single OpenAI‑compatible API. It handles routing, usage/cost tracking, fine‑grained access control, and offers a multilingual web console plus extensible JavaScript task plugins. Deployable via Docker or Docker‑Compose, it’s built with Go (backend) and React/Bun (frontend) and is licensed under AGPL‑v3.

  • Project
    diegosouzapw/OmniRoute

    An AI gateway that provides a single endpoint to access 370+ AI providers and 150+ free tiers with automatic fallback and token compression.

  • Project
    astaxie/TokenHub

    TokenHub is an open‑source, Go‑based gateway that adds enterprise‑level governance (routing, permissions, budgeting, and bill reconciliation) to any OpenAI‑compatible LLM provider. It offers role‑aware consoles, OpenAI‑compatible APIs, SQLite/PostgreSQL deployment options, and Docker‑Compose or systemd installers.

  • Project
    Continuum-AI-Corp/OrcaRouter-Lite

    A self-hosted, OpenAI-compatible LLM router that automates model selection based on cost and capability, providing a unified API for multiple AI providers.

  • Project
    OnyxAxisOwO/ObsidianArc

    A self-hosted multi-user AI chat service and API gateway that aggregates multiple AI providers into a single, lightweight Go binary with built-in user and quota management.