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

# API overview

> AIOHub API basics: Base URLs, formats, authentication, requests, and responses.

## Entry points

Use the base URL for your SDK or client. Do not add paths from another API format.

| Use case                             | Base URL                               | Common endpoint                               |
| ------------------------------------ | -------------------------------------- | --------------------------------------------- |
| OpenAI SDK / OpenAI-compatible tools | `https://api.aiohub.org/v1`            | `POST /chat/completions`                      |
| Codex CLI                            | `https://api.aiohub.org/v1`            | `POST /responses`                             |
| Anthropic SDK / Claude Code          | `https://api.aiohub.org`               | `POST /v1/messages`                           |
| Gemini CLI                           | `https://api.aiohub.org`               | `POST /v1beta/models/{model}:generateContent` |
| Gemini REST / Google SDK             | `https://api.aiohub.org/v1beta`        | `POST /models/{model}:generateContent`        |
| Console dashboard                    | `https://api.aiohub.org/console`       | Account overview                              |
| API key management                   | `https://api.aiohub.org/console/token` | Create and manage API keys                    |
| Wallet management                    | `https://api.aiohub.org/console/topup` | Balance, add funds, and payment history       |
| Usage logs                           | `https://api.aiohub.org/console/log`   | Usage records and costs                       |

## Supported API formats

| Format            | Endpoint                                      | Use case                                      |
| ----------------- | --------------------------------------------- | --------------------------------------------- |
| OpenAI compatible | `POST /v1/chat/completions`                   | Default for most SDKs and tools               |
| OpenAI Responses  | `POST /v1/responses`                          | Codex CLI and clients using the Responses API |
| Claude Messages   | `POST /v1/messages`                           | Claude Code and Anthropic SDK                 |
| Gemini API        | `POST /v1beta/models/{model}:generateContent` | Gemini CLI and Google SDK                     |

<Tip>If you are unsure which format to use, start with OpenAI Chat Completions for a basic chat request. Codex CLI uses Responses, not Chat Completions.</Tip>

## Authentication

AIOHub API keys start with `sk-`. Different clients use different headers with the same API key value:

| Method                | Header                                   | Client                               |
| --------------------- | ---------------------------------------- | ------------------------------------ |
| Bearer auth           | `Authorization: Bearer sk-xxx`           | OpenAI SDK, Codex CLI, most tools    |
| Anthropic API Key     | `x-api-key: sk-xxx`                      | Anthropic SDK                        |
| Anthropic bearer auth | `Authorization: Bearer sk-xxx`           | Claude Code (`ANTHROPIC_AUTH_TOKEN`) |
| Google API Key        | `x-goog-api-key: sk-xxx` or `key=sk-xxx` | Gemini CLI, Google SDK               |

See [Authentication](/en/api/authentication) for examples.

## Request example

```bash theme={"system"}
curl https://api.aiohub.org/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

## Response shape

Successful responses follow the selected compatible API format. For example, an OpenAI Chat Completions response looks like:

```json theme={"system"}
{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12,
    "total_tokens": 22
  }
}
```

## Streaming responses

Chat Completions supports SSE streaming. Set `"stream": true`:

```bash theme={"system"}
curl https://api.aiohub.org/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'
```

## Error responses

Error responses include an HTTP status code and a JSON error body:

```json theme={"system"}
{
  "error": {
    "message": "Incorrect API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}
```

See [HTTP status codes](/en/support/http-status-codes) for common status codes and retry guidance.

## Public endpoint scope

The API reference navigation lists the main user-facing endpoints. Available models, groups assigned to your API key, and endpoints depend on `/v1/models`, the console pricing page, and the current service state. Unlisted compatibility routes are not officially supported.