> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Openference gives you one OpenAI-compatible endpoint for curated models from leading AI labs — GLM, DeepSeek, Kimi, Qwen, MiniMax, and more — with intelligent failover, simple plan-based billing, and instant API keys.

# Welcome to Openference

Openference is a curated AI model proxy. It provides a single, stable, OpenAI-compatible API endpoint that intelligently routes your requests to the best available upstream providers.

**One base URL. One API key. Many models.**

## Why Openference?

* **Drop-in compatible**: Works with Cursor, Claude Code, Codex, Cline, OpenCode, Pi, and similar coding tools.
* **Curated catalog**: Hand-picked high-quality models across providers. We handle deprecations so you don't have to.
* **Automatic failover & key rotation**: If one upstream provider is down or rate-limited, we route to healthy alternatives.
* **Transparent pricing**: Plan-based pricing with included usage, plus clear on-demand rates for every model when you need more. No surprise bills.
* **Usage separation**: Plan quotas vs on-demand credits are tracked distinctly.
* **Format translation**: Send OpenAI format to Anthropic-format models (and vice-versa). We convert for you.
* **Fast & global**: Runs on a globally distributed edge network for low latency worldwide.

## Supported API surfaces

| Endpoint                    | Format    | Notes                                                 |
| --------------------------- | --------- | ----------------------------------------------------- |
| `POST /v1/chat/completions` | OpenAI    | Primary chat interface, streaming, tools              |
| `POST /v1/messages`         | Anthropic | Claude-style messages                                 |
| `POST /v1/responses`        | OpenAI    | Responses API (Codex etc.)                            |
| `POST /v1/embeddings`       | OpenAI    | Text embeddings                                       |
| `GET /v1/models`            | OpenAI    | Live model list (filtered by your key's restrictions) |

All endpoints are available at:

```
https://api.openference.com/v1
```

## Get started in 60 seconds

1. [Register](https://openference.com/register) and verify your email.
2. Log in and create an API key in the dashboard.
3. Point your coding tool at `https://api.openference.com/v1` — works with Cursor, Claude Code, Codex, OpenCode, Pi, Cline, and similar.

See the [Quickstart](/quickstart) for full walkthroughs with popular clients.

## Next steps

* Read [Base URL & Authentication](/getting-started/base-url-auth)
* Browse [Client Integrations](/integrations/cursor) (start with Cursor)
* Explore the live [Models catalog](https://openference.com/models)
* Review [Pricing & Plans](https://openference.com/pricing)

Questions? Check the [FAQ](/faq) or [Troubleshooting](/troubleshooting/common-errors).