Getting started
Introduction
What RouterPlex is and how it fits into your stack.
RouterPlex is a drop-in replacement for the OpenAI API. One endpoint, one key, one balance — every model we serve, from GPT and Claude to Gemini, DeepSeek, Kimi and Qwen.
Base URL: https://api.routerplex.com/v1 — if your code works with OpenAI, point it here and it works with RouterPlex.
How it works #
- You create an API key in the dashboard.
- You point any OpenAI-compatible SDK, IDE, or agent at
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 request deducts its exact token cost from your prepaid balance. No subscriptions.
What's supported #
| Capability | Status |
|---|---|
Chat completions (/v1/chat/completions) | All 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 |
Model list (/v1/models) | Supported |
Anthropic-native /v1/messages format | Not supported — use the OpenAI format for Claude models |
Where to go next #
- Quickstart — first request in under a minute.
- 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.