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

# Cline Integration Guide

> Configure Cline VS Code extension with Infercom's EU sovereign inference. Autonomous AI coding assistant with Plan/Act modes and GDPR compliance.

[Cline](https://cline.bot) is a VS Code extension that provides an autonomous AI coding assistant. It can read files, write code, run commands, and iterate on its work.

<Info>
  **Setup time:** \~2 minutes
</Info>

## Prerequisites

* [VS Code](https://code.visualstudio.com/) installed
* [Cline extension](https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev) installed
* [Infercom API key](https://cloud.infercom.ai/apis)

## Configuration

### Step 1: Open Cline Settings

1. Open VS Code
2. Click the Cline icon in the sidebar
3. Click the **gear icon** to open settings

### Step 2: Select Provider

1. In the **API Provider** dropdown, select **OpenAI Compatible**
2. Enter the base URL: `https://api.infercom.ai/v1`
3. Enter your **Infercom API key**
4. Enter the model name: `MiniMax-M2.7`

### Step 3: Model Configuration

Under **Model Configuration**:

| Setting                 | Value    |
| ----------------------- | -------- |
| **Context Window Size** | `192000` |
| **Support Images**      | Disabled |
| **Enable R1 Format**    | Disabled |

<Warning>
  **Support Images** must be disabled - MiniMax-M2.7 doesn't support image input.
</Warning>

### Step 4: Verify Connection

Click **Test Connection** or start a conversation to verify the setup works.

<Tip>
  This single-model setup is the simplest option and works well for most tasks. For complex projects, see the Plan/Act configuration below.
</Tip>

## Optional: Plan/Act Modes

For complex tasks, Cline supports separate models for planning and execution. Use a frontier model (Claude, GPT, Gemini) for planning and MiniMax-M2.7 on Infercom for fast code generation.

### Enable Plan/Act Modes

1. In Cline settings, toggle **"Use different models for Plan and Act modes"**
2. Configure each mode separately:

| Mode     | Provider                     | Model               | Purpose                                             |
| -------- | ---------------------------- | ------------------- | --------------------------------------------------- |
| **Plan** | Your preferred provider      | Claude, GPT, Gemini | Deep reasoning for architecture decisions           |
| **Act**  | OpenAI Compatible (Infercom) | `MiniMax-M2.7`      | Fast code generation on EU sovereign infrastructure |

<Tip>
  Cline preserves planning context when switching into Act mode, so MiniMax-M2.7 can continue from the plan instead of starting from scratch.
</Tip>

## Model

Use `MiniMax-M2.7` - optimized for agentic coding with 192K context window.

## Usage

With Cline configured:

1. Click the Cline icon in VS Code sidebar
2. Type your request in the chat
3. Cline will autonomously:
   * Read relevant files
   * Write or edit code
   * Run terminal commands
   * Iterate until the task is complete

### Example Tasks

* "Add error handling to the login function"
* "Write unit tests for the User class"
* "Refactor this file to use async/await"

## Troubleshooting

### Connection Failed

Verify your configuration:

* Base URL: `https://api.infercom.ai/v1`
* API key is valid
* Model name is exact: `MiniMax-M2.7`

### Model Not Found

Ensure the model name matches exactly (case-sensitive): `MiniMax-M2.7`

### Slow Responses

MiniMax-M2.7 runs at 400+ tokens/sec. If responses seem slow:

1. Check your network connection
2. Large context (many files) increases processing time
3. First request may be slower due to model loading

## Next Steps

* [Cursor](/en/agentic-coding/cursor) - Full AI-native IDE
* [Continue](/en/agentic-coding/continue) - Open-source alternative
* [Choosing a Tool](/en/agentic-coding/choosing-a-tool) - Compare all options