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

# Integration overview

> Choose the correct NexusAPI URL and protocol for your client or application.

NexusAPI supports common AI clients and OpenAI-style API calls. Different clients append different paths automatically, so choose the address from the guide for the tool you are using.

## Before you start

Whichever method you use, make sure that you have:

1. Created an API key in the console.
2. Chosen a token group that includes the target model.
3. Copied the exact model ID from the Model Marketplace.
4. Confirmed the model's supported protocol before sending a request.

## Choose your entry point

| What you are doing               | Read this                                         |
| -------------------------------- | ------------------------------------------------- |
| Building a script or application | [Quick start](/en/guide/quick-start)              |
| Configuring Claude Code          | [Claude Code guide](/en/tools/claude-code)        |
| Configuring Codex CLI            | [Codex CLI guide](/en/tools/codex-cli)            |
| Managing several CLI providers   | [CC Switch guide](/en/tools/cc-switch)            |
| Using VS Code or Cursor          | [VS Code / Cursor guide](/en/tools/cursor-vscode) |
| Generating images                | [Image model guide](/en/guide/image-generation)   |

## URL and protocol reference

\| Scenario | Base URL to enter | Main protocol | Important note |
\| --- | --- | --- |
\| OpenAI SDK or a general text application | `https://nexusapi.link/v1` | Chat Completions | Your SDK normally appends the request path. |
\| Codex CLI | `https://nexusapi.link/v1` | Responses | Use the provider settings from the Codex guide. |
\| Claude Code | `https://nexusapi.link` | Anthropic Messages | Do not append `/v1` again in the Claude Code setting. |
\| CC Switch | Depends on the selected app | Depends on the app | Claude and Codex use different URL rules. |
\| Image models | `https://nexusapi.link/v1` | Images | Use only a model explicitly marked for image generation. |

Before relying on an endpoint, check the [API and model capability matrix](/en/developer/capability-matrix). It explains what NexusAPI currently documents as an external capability; the Model Marketplace remains the source of truth for a specific key and model.

## Pick the protocol first

The same domain does not mean that every model accepts every request format.

| Your goal                                | Recommended endpoint     | Use it when                                                 |
| ---------------------------------------- | ------------------------ | ----------------------------------------------------------- |
| General text, chat, or streaming         | `/v1/chat/completions`   | The model is available through the OpenAI-compatible route. |
| Codex CLI and a matching provider        | `/v1/responses`          | The client and selected model are configured for Responses. |
| Claude Code or a native Anthropic client | `/v1/messages`           | The model is available through the Anthropic route.         |
| Image generation                         | `/v1/images/generations` | The model is explicitly marked as image-capable.            |

<Warning>
  **Do not use Responses as a universal replacement for Claude**

  If a current Anthropic-type Claude channel returns `status_code=500, not implemented` through `/v1/responses`, switch a custom application to `/v1/chat/completions`, or keep Claude Code on its native Messages configuration. Repeating the same request will not make this protocol mismatch recover.
</Warning>

## Why URLs can look different

Most OpenAI-style applications use:

```text theme={"system"}
https://nexusapi.link/v1
```

Some clients require the site URL without `/v1`, or add `/chat/completions`, `/responses`, or `/messages` themselves. Follow the tool-specific guide rather than copying an address from another client.

<Warning>
  **Avoid duplicate paths**

  If a client already appends `/v1`, entering a URL that includes it can produce `/v1/v1/...` and a 404 error. Check the actual request URL first when you see a 404.
</Warning>

## Confirm that the setup works

* The client returns a complete response.
* The matching request appears in the console usage log.
* The model, token group, and charge match your expectation.

If it fails, keep the error text and Request ID, then use the [self-check guide](/en/faq/self-check).