RouteMux icon

RouteMux

RouteMux is an AI gateway for models from multiple providers through one API key and base URL, with centralized billing and redundant routing.

RouteMux

AI model access through one gateway

RouteMux is an AI gateway that provides one API key and base URL for accessing models from multiple providers. It presents OpenAI-compatible access alongside Anthropic-compatible and Google Vertex AI protocol options, allowing teams to evaluate or adopt different models without maintaining a separate gateway integration for each provider.

The service combines a model catalog with centralized prepaid billing, request and usage visibility, and routing designed with redundancy across the network, gateway, and model-service layers. It covers text, image, video, and audio workloads, although protocol support, inputs, outputs, pricing units, and capabilities vary by model and should be checked in the catalog and documentation.

Key features

Unified model gateway

Use one API key and base URL to reach models from providers including OpenAI, Anthropic, Google, MiniMax, DeepSeek, xAI, Moonshot, Qwen, Zhipu, and Meta, subject to the current catalog.

Multiple protocol paths

The catalog lists OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, Google Vertex AI, image, Sora video, speech, and transcription protocol categories.

Redundant routing

RouteMux describes redundancy across network, gateway, and model-service layers, with health-aware routing across vendors intended to support failover and recovery during interruptions.

Centralized billing

A shared prepaid wallet supports model-family access from one account, while the pricing pages display RouteMux and official provider rates for supported models.

Console visibility

The homepage exposes API keys, logs, usage, billing, and activity areas in its console, providing a central place to monitor requests and spending.

Multimodal model catalog

The catalog includes text, image, video, and audio models, with filters for capabilities such as vision, reasoning, tool calling, JSON mode, video input, prompt caching, and context length.

Practical use cases

  • Model evaluation and prototyping

    Prototype a text, vision, reasoning, or tool-calling application against one gateway, then compare models from different providers without adding a separate provider integration for each test.

  • Resilient application backends

    Run production workloads that need routing across vendors and a recovery path when a network, gateway, or model-service layer has an interruption.

  • Multimodal workflows

    Build applications that combine language models with image generation, video generation, speech, or transcription while managing access through a single account.

  • Usage and cost operations

    Give engineering or operations teams a shared place to manage API keys and review logs, usage, activity, and billing for model calls.

  • Provider and cost comparison

    Use the catalog and pricing comparisons to select models by protocol, capability, context length, modality, or listed rate before connecting them to an application.

Pros and Cons

Pros

  • One integration can expose models from multiple providers and protocol families.
  • Health-aware, multi-layer redundancy is designed to reduce the effect of provider or service interruptions.
  • A shared wallet, usage console, logs, and billing view consolidate operational monitoring.
  • The catalog spans text, image, video, and audio models, with filters for several practical capabilities.
  • Unused account balance can be withdrawn, and the homepage states that only successful requests are billed.

Cons

  • The catalog and pricing are model-specific: supported protocols, capabilities, context lengths, outputs, and billing units differ across entries.
  • The service uses prepaid wallet billing, so users need to fund an account before making usage-based calls.
  • The source material does not establish universal limits, guaranteed availability, or identical compatibility across every listed model.

FAQ

Which API protocols does RouteMux support?

RouteMux provides a unified gateway for accessing models through OpenAI-compatible, Anthropic-compatible, and Google Vertex AI protocols. The models directory lists supported protocol types, while exact request details should be checked in the documentation for the selected model.

How does a typical RouteMux integration work?

The site describes a single API key and base URL for model access. It also provides documentation and an llms.txt resource intended to explain the base URL, model names, billing rules, and OpenAI-compatible Python usage.

How is RouteMux usage billed?

RouteMux uses a prepaid wallet. The pricing page presents per-token rates for applicable text models and notes that final charges follow actual usage; image and video entries may use different units such as per call or per second.

What happens to unused balance?

The homepage states that only successful requests are billed and that unused account balance can be withdrawn at any time. The site also advertises a first-top-up promotional credit offer subject to stated signup, timing, minimum-top-up, and account conditions; promotions may change.

What kinds of models and capabilities are available?

RouteMux lists text, image, video, and audio model categories, with capabilities such as vision, reasoning, tool calling, JSON mode, video input, and prompt caching shown in its model catalog. Availability and compatibility vary by model.

Quick Facts

Category
AI gateway and developer tool
Access model
One API key and base URL for multiple model providers
Protocols listed
OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, Google Vertex AI, image, video, speech, and transcription paths
Modalities
Text, image, video, and audio
Billing
Prepaid wallet with usage-based rates; units vary by model
Source domain
routemux.com