Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.inferoute.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

TokenHub is an AI inference routing platform that gives you one unified API endpoint for all major LLM providers — OpenAI, Anthropic, Google, Mistral, and more. Instead of maintaining separate accounts, credentials, and integration code for each provider, you point your application at TokenHub and it handles the routing, fallback, and cost optimization automatically.

​
Why use TokenHub

Managing multiple LLM providers directly means juggling different API formats, rate limits, billing accounts, and failure modes. TokenHub replaces that complexity with a single OpenAI-compatible endpoint. Because the API matches the OpenAI standard, you can switch to TokenHub without changing your existing application code — just update the base URL and API key. TokenHub routes each request based on the criteria you care about most: lowest cost, lowest latency, or highest availability. When a provider is degraded or rate-limiting you, TokenHub automatically retries with a configured fallback so your application stays responsive.

​
Who it’s for

TokenHub is designed for developers and teams building AI-powered applications who want to:
  • Use multiple LLM providers without maintaining separate integrations
  • Reduce inference costs by routing to more affordable models when appropriate
  • Improve reliability with automatic failover across providers
  • Track token usage and spending across all providers in one dashboard

​
Key benefits

  • OpenAI-compatible API — works with any OpenAI SDK or HTTP client with no code changes
  • No vendor lock-in — switch providers or add new ones through the dashboard without touching your application
  • Automatic fallback — requests retry against backup providers when a primary provider fails
  • Usage tracking — monitor token consumption and costs across all providers from a single dashboard

​
Get started

Quickstart

Make your first API call through TokenHub in under five minutes.

Authentication

Generate an API key and learn how to authenticate every request.

Routing concepts

Understand how TokenHub selects providers for each request.

API reference

Explore the full OpenAI-compatible REST API.