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

# Anthropic API Compatibility (Beta)

## Overview

To meet developers’ needs for leveraging the Anthropic API ecosystem, our API now supports accessing **all models via the Anthropic API interface**.\
It supports **200+ LLMs**, including **7 free models**.

## Quick Start

### Install the Anthropic SDK

<CodeGroup>
  ```shellscript Python theme={null}
  pip install -U anthropic
  ```

  ```shellscript Node.js theme={null}
  npm install @anthropic-ai/sdk
  ```
</CodeGroup>

### API Usage

**Endpoint:** `https://aihubmix.com/v1/messages`

<CodeGroup>
  ```shellscript Curl theme={null}
  curl https://aihubmix.com/v1/messages \
    -H "Content-Type: application/json" \
    -H "x-api-key: <AIHUBMIX_API_KEY>" \
    -H "anthropic-version: 2023-06-01" \
    -d '{
      "model": "minimax-m2.1",
      "max_tokens": 16000,
      "thinking": {
        "type": "enabled",
        "budget_tokens": 10000
      },
      "messages": [
        {
          "role": "user",
          "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?"
        }
      ]
    }'
  ```

  ```python Python theme={null}
  from anthropic import Anthropic

  client = Anthropic(
    api_key="<AIHUBMIX_API_KEY>",
    base_url="https://aihubmix.com"
  )

  response = client.messages.create(
    model="glm-4.7",
    max_tokens=16000,
    thinking={
        "type": "enabled",
        "budget_tokens": 10000
    },
    messages=[
        {
            "role": "user",
            "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?"
        }
    ]
  )

  # The response contains summarized thinking blocks and text blocks
  for block in response.content:
      if block.type == "thinking":
          print(f"\nThinking summary: {block.thinking}")
      elif block.type == "text":
          print(f"\nResponse: {block.text}")
  ```
</CodeGroup>

## Compatibility Notes

### Supported Parameters

When integrating via the Anthropic API, the following input parameters are supported:

| Parameter     | Type                              | Required | Description                                                                    |
| ------------- | --------------------------------- | -------- | ------------------------------------------------------------------------------ |
| `model`       | string                            | Yes      | Supported models can be found in the [Model List](https://aihubmix.com/models) |
| `messages`    | array of MessageParam             | Yes      | Input messages                                                                 |
| `max_tokens`  | number                            | No       | Maximum number of tokens to generate                                           |
| `stream`      | boolean                           | No       | Enable streaming responses                                                     |
| `system`      | string or array of TextBlockParam | Yes      | System prompt                                                                  |
| `temperature` | number                            | No       | Range: (0.0, 1.0]. Controls output randomness; recommended value is 1          |
| `top_p`       | number                            | No       | Nucleus sampling parameter                                                     |
| `thinking`    | ThinkingConfigParam               | No       | Reasoning configuration                                                        |

### Supported Message Types

| Type                 | Description            |
| -------------------- | ---------------------- |
| `type="text"`        | Text message           |
| `type="tool_use"`    | Tool invocation        |
| `type="tool_result"` | Tool invocation result |
| `type="thinking"`    | Model reasoning output |

## Usage Example

### Using GPT-5.2 in Claude Code

Although any supported model can be used via AIHubMix, for the best experience we recommend high-capability models such as **gpt-5.2** or **glm-4.7**.

#### 1. Install and Configure Claude Code

Refer to the Claude Code installation guide: [https://docs.aihubmix.com/cn/api/Claude-Code](https://docs.aihubmix.com/cn/api/Claude-Code)

#### 2. Connect Claude Code to AIHubMix

**Claude configuration file:** `.claude/settings.json`

```json theme={null}
{
  "env": {
    "ANTHROPIC_API_KEY": "AIHUBMIX_API_KEY",
    "ANTHROPIC_BASE_URL": "https://aihubmix.com",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "gpt-5.2",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "gpt-5.2",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "gpt-5.2",
    "ANTHROPIC_MODEL": "gpt-5.2"
  },
  "includeCoAuthoredBy": false
}
```

Replace `AIHUBMIX_API_KEY` with your actual AIHubMix API key.

<Tip>
  The native Claude Code installer cannot read standard `.env` files. Do not place these settings in a `.env` file.
</Tip>

#### 3. Start a Conversation

Navigate to your project directory and launch Claude Code:

```bash theme={null}
$ cd /path/to/your-project
> claude
```

Once connected successfully, all prompts you send will be routed through AIHubMix.

#### 4. Verification

You can verify the connection by running the `/status` command in Claude Code:

```bash theme={null}
> /status

 API key: ANTHROPIC_API_KEY
 Anthropic base URL: https://aihubmix.com

 Model: gpt-5.2
```

***

Last updated: 2026-06-01