> ## 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.

# CLI & IDE Compatibility Matrix

> Quick reference for which clients are supported and what endpoints they need.

# CLI & IDE Compatibility Matrix

Reference for Openference client integration and verify flows.

| Client            | Verify / smoke test              | Endpoint(s) needed                   | Status                                   |
| ----------------- | -------------------------------- | ------------------------------------ | ---------------------------------------- |
| Cursor            | `GET /v1/models` + Bearer        | `/v1/models`, `/v1/chat/completions` | Full                                     |
| Cline             | `GET /v1/models` or chat         | `/v1/models`, `/v1/chat/completions` | Full                                     |
| Codex CLI         | `GET /v1/models` or `/responses` | `/v1/models`, `/v1/responses`\*      | Full                                     |
| Claude Code       | chat via Messages API            | `/v1/messages`                       | Full                                     |
| OpenCode CLI      | `GET /v1/models` or chat         | `/v1/models`, `/v1/chat/completions` | Full                                     |
| Kilo CLI          | `GET /v1/models` or chat         | `/v1/models`, `/v1/chat/completions` | Full                                     |
| Pi                | `GET /v1/models` or chat         | `/v1/models`, `/v1/chat/completions` | Full                                     |
| Open WebUI        | `GET /v1/models` or chat         | `/v1/models`, `/v1/chat/completions` | Full (custom User-Agent header required) |
| OpenAI Embeddings | `POST /v1/embeddings`            | `/v1/embeddings`                     | Full                                     |
| LiteLLM / generic | chat + models                    | existing                             | Full                                     |

\* Codex `POST /v1/responses` is adapted to chat completions for Chinese-model upstreams. See [Chinese LLM Models](/integrations/chinese-models).

## Base URL convention

All clients should use:

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

API keys are opaque strings (create in the dashboard).

## Usage counting

Requests count toward your plan's window allowance when they succeed or fail with a client error (4xx). Upstream failures and capacity errors do not count.

## Cursor verify

Cursor's Verify button calls `GET {base_url}/models` with the configured Bearer token. Openference returns an OpenAI-compatible model list filtered by token restrictions. Each model includes `permission: []`, `root`, and `parent: null` so Cursor's client-side checks do not crash on missing fields.

## Detailed guides

See the individual pages:

* [Cursor](/integrations/cursor)
* [Chinese LLM Models](/integrations/chinese-models)
* [OpenCode CLI](/integrations/opencode)
* [Codex](/integrations/codex)
* [Kilo CLI](/integrations/kilo-cli)
* [Pi](/integrations/pi)
* [Open WebUI](/integrations/open-webui)
* And others in the sidebar.

## Model configuration tip

When a client lets you list specific models (e.g. OpenCode), only list the models you actually use. The model keys must exactly match the IDs returned by `GET /v1/models`.