Introduction
What RouterPlex is and how it fits into your stack.
A clear path through the docs
Start with what you need
New to RouterPlex? Start with Quickstart. Already have a client? Jump to the matching setup guide.
01 / first request
Quickstart
Create a key, connect your client, and send your first request.
02 / keep access safe
Authentication
Learn which headers to use and how to isolate keys by app or agent.
03 / use your stack
Connect your tool
Find your editor, agent, or SDK and follow the steps for your OS.
04 / go deeper
API reference
Explore endpoints, streaming, tools, vision, models, and errors.
On this page
RouterPlex is an AI gateway: one API key for 62 models from OpenAI, Google, Anthropic and other providers through a single OpenAI-compatible endpoint. One step to integrate — point existing code at the endpoint — then switch models with a one-line change as new routes ship. Always-on hosted infrastructure, with token prices at vendor list and a built-in optimization layer that automatically routes requests to cut cost by up to 40% with no quality loss — included for every account.
OpenAI base URL: https://api.routerplex.com/v1
>
Anthropic base URL: https://api.routerplex.com — the Anthropic SDK appends /v1/messages.
How it works #
- You create an account and verify your email.
- Open guided setup, choose your tool, and create a dedicated key. Eligible verified accounts receive $1 in test credit once.
- Follow the configuration for your tool and send a short request. Top up from $5 by card or $15 by crypto to continue using the same key. OpenAI-compatible clients use
https://api.routerplex.com/v1. - You pick a model by its ID (for example
gpt-5.5,claude-opus-4-8,gemini-3.1-pro) — same request shape for all of them. - Every paid request deducts its exact token cost from your prepaid balance. No subscription required.
What's supported #
| Capability | Status |
|---|---|
Chat completions (/v1/chat/completions) | All 61 chat models |
| Streaming (SSE) | Supported |
| Function calling / tools | Supported, model-dependent |
| Vision (image inputs) | Supported, model-dependent |
| JSON mode / structured output | Supported, model-dependent |
Image generation (/v1/images/generations) | Supported — gpt-image-2 |
Responses API (/v1/responses) | Supported for Codex custom providers |
Model list (/v1/models) | Supported |
Anthropic-compatible /v1/messages format | All 61 chat models — use the Anthropic SDK or point Claude Code straight at RouterPlex |
Where to go next #
- Quickstart — first request in under a minute.
- Setup prompts — paste one prompt and let your coding agent do the setup.
- Anthropic Messages — call any chat model with the Anthropic SDK and wire format.
- IDEs & editors and Agents & CLIs — use RouterPlex inside Cursor, VS Code, Zed, OpenClaw, OpenCode, Codex CLI, Aider and more.
- Models — the live catalog with per-token pricing.