> ## 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.

# Claude Code Integration Guide

> Route Claude Code requests through Infercom's EU sovereign infrastructure using ccproxy. Advanced setup for agentic coding with full EU data sovereignty.

<Warning>
  **Advanced Setup** - This integration requires running a local proxy. For simpler setups, consider [Aider](/en/agentic-coding/aider) or [OpenCode](/en/agentic-coding/opencode).
</Warning>

[Claude Code](https://claude.ai/claude-code) is Anthropic's official CLI for AI-assisted coding. While it's designed for Claude models, you can route requests to Infercom using [ccproxy](https://github.com/ryoppippi/ccproxy), a LiteLLM-based proxy.

## How It Works

ccproxy intercepts Claude Code's API calls and routes them to your configured provider (Infercom). This allows you to use Claude Code's interface while running inference on EU sovereign infrastructure.

```
Claude Code CLI -> ccproxy (localhost) -> Infercom API
```

## Prerequisites

* [Claude Code CLI](https://claude.ai/claude-code) installed
* [Infercom API key](https://cloud.infercom.ai/apis)
* Node.js 18+ or Bun

## Installation

### Step 1: Install ccproxy

```bash theme={null}
# Using npm
npm install -g ccproxy

# Or using Bun
bun install -g ccproxy
```

### Step 2: Create Configuration

Create `~/.ccproxy/config.yaml`:

```yaml theme={null}
model_list:
  # Route Sonnet requests to Infercom MiniMax
  - model_name: infercom
    litellm_params:
      model: openai/MiniMax-M2.7
      api_base: https://api.infercom.ai/v1
      api_key: "your-infercom-api-key"

  # Keep Claude models for complex tasks (optional)
  - model_name: claude-sonnet-4-6
    litellm_params:
      model: anthropic/claude-sonnet-4-6
      api_base: https://api.anthropic.com
      api_key: "your-anthropic-api-key"

litellm_settings:
  drop_params: true  # Required - drops unsupported params like reasoning_effort
```

Create `~/.ccproxy/ccproxy.yaml` for routing rules:

```yaml theme={null}
ccproxy:
  rules:
    # Route Sonnet to Infercom
    - name: infercom
      rule: ccproxy.rules.MatchModelRule
      params:
        - model_name: claude-sonnet-4-6

litellm:
  host: 127.0.0.1
  port: 4000
```

<Tip>
  `drop_params: true` is required because MiniMax doesn't support all Claude parameters like `reasoning_effort`.
</Tip>

<Tip>
  Map multiple Claude model names to ensure compatibility with different Claude Code versions.
</Tip>

### Step 3: Start ccproxy

```bash theme={null}
cd ~/.ccproxy && ccproxy start
```

You should see:

```
ccproxy running on http://127.0.0.1:4000
```

Keep this terminal open while using Claude Code.

## Usage

### Configure Claude Code

In a new terminal, set the API endpoint:

```bash theme={null}
export ANTHROPIC_BASE_URL="http://127.0.0.1:4000"
```

### Run Claude Code

```bash theme={null}
claude
```

### Switch Models

Use the `/model` command in Claude Code to select a model. The model name will show as "Claude" but requests are routed to MiniMax-M2.7.

## Running ccproxy as a Service

### macOS (launchd)

Create `~/Library/LaunchAgents/com.ccproxy.plist`:

```xml theme={null}
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>Label</key>
    <string>com.ccproxy</string>
    <key>ProgramArguments</key>
    <array>
        <string>/usr/local/bin/ccproxy</string>
    </array>
    <key>RunAtLoad</key>
    <true/>
    <key>KeepAlive</key>
    <true/>
</dict>
</plist>
```

Load the service:

```bash theme={null}
launchctl load ~/Library/LaunchAgents/com.ccproxy.plist
```

### Linux (systemd)

Create `~/.config/systemd/user/ccproxy.service`:

```ini theme={null}
[Unit]
Description=ccproxy for Claude Code
After=network.target

[Service]
ExecStart=/usr/local/bin/ccproxy
Restart=always

[Install]
WantedBy=default.target
```

Enable and start:

```bash theme={null}
systemctl --user enable ccproxy
systemctl --user start ccproxy
```

## Limitations

<Warning>
  **Known Limitations:**

  * Model name displays as "Claude" in the interface even when using Infercom
  * Some Claude-specific features may not work (vision, computer use)
  * Requires keeping proxy running
  * VS Code extension is less reliable than CLI
</Warning>

## Troubleshooting

### Connection Refused

Ensure ccproxy is running:

```bash theme={null}
curl http://127.0.0.1:4000/health
```

### Authentication Errors

Verify your Infercom API key in `ccproxy.yaml`:

```bash theme={null}
curl -s https://api.infercom.ai/v1/models \
  -H "Authorization: Bearer your-infercom-api-key"
```

### Model Not Found

Check that your `ccproxy.yaml` maps the correct Claude model names:

```yaml theme={null}
model_name: "claude-sonnet-4-20250514"  # Must match what Claude Code requests
```

### Slow Responses

ccproxy adds minimal latency. If responses are slow, check:

1. Your network connection to `api.infercom.ai`
2. Model load times (first request may be slower)

## Security Considerations

* ccproxy runs locally and doesn't expose your API key to external services
* All traffic to Infercom is encrypted (HTTPS)
* Your code stays within the EU infrastructure

## Alternative: Direct API

For simpler setups without the proxy overhead, consider:

* [Aider](/en/agentic-coding/aider) - 2 minute setup
* [OpenCode](/en/agentic-coding/opencode) - Full TUI experience

## Next Steps

* [Choosing a Tool](/en/agentic-coding/choosing-a-tool) - Compare all options
* [API Reference](/en/api-reference/overview) - Direct API usage