This tutorial walks you through using Cast AI's Serverless Endpoints with Cline, an agentic coding tool available as a standalone CLI and as a VS Code extension. You'll configure Cline to use Qwen 3 Coder via AI Enabler, providing a cost-effective setup for AI-assisted development.

Overview

By the end of this tutorial, you'll be able to:

• Authenticate Cline against AI Enabler as a model provider
• Use Qwen 3 Coder Next for code generation and execution tasks
• Run Cline interactively in your terminal or headlessly in scripts and CI/CD pipelines

This tutorial focuses on Cline CLI. If you use Cline inside an IDE, see IDE integration.

This tutorial is intended for developers familiar with command-line tools. It assumes basic knowledge of how LLM-based coding assistants work.

Prerequisites

Before starting, ensure you have:

1. A Cast AI API key — Generate one from the Cast AI console under AI Enabler > Overview

   

2. Node.js 20 or higher — Check your version with node --version.

3. Cline CLI installed — Install globally via npm:

   Shell

   npm install -g cline

Verify the installation:

cline version

📘

Note

Serverless Endpoints work with any OpenAI-compatible client. This tutorial covers Cline, but the same AI Enabler base URL and API key work with OpenCode and other compatible tools.

Step 1: Authenticate Cline with AI Enabler

Unlike tools that use a JSON config file, Cline manages provider configuration through its auth command. Run the following to point Cline at AI Enabler's OpenAI-compatible endpoint:

cline auth -p openai -k YOUR_CASTAI_API_KEY -b https://llm.cast.ai/openai/v1 -m qwen3-coder-next-fp8

Here's what each flag does:

Replace YOUR_CASTAI_API_KEY with the key you generated from the Cast AI console.

Step 2: Verify your configuration

Confirm that Cline stored your settings correctly:

cline config

You should see https://llm.cast.ai/openai/v1 as the openAiBaseUrl and qwen3-coder-next-fp8 as the planModeOpenAiModelId. If something looks wrong, re-run the cline auth command from Step 1. It overwrites the stored configuration.

Global Settings:
	actModeApiProvider: openai
  actModeOpenAiModelId: qwen3-coder-next-fp8
	[...]
  openAiBaseUrl: https://llm.cast.ai/openai/v1

Step 3: Test the connection

Navigate to a project directory and run a simple test to confirm the connection to AI Enabler is working:

cd ~/your-project
cline "What files are in this directory?"

This is intentionally lightweight. It doesn't require Cline to write or modify any code, so if something goes wrong, you'll know immediately it's a connectivity or auth issue rather than a model behavior issue.

Once that succeeds, try a prompt that requires a real inference call:

cline "Explain what this project does in one paragraph"

Using Cline

Cline operates in two modes depending on how you invoke it.

Interactive mode launches a full terminal interface for hands-on development sessions. Start it by running cline with no arguments from your project directory:

cline

In interactive mode, you can type tasks, review Cline's plan before it acts, and toggle between Plan and Act modes with Tab, and use /settings to adjust your configuration without leaving the session. For more information on Cline's Interactive mode, see Cline documentation.

Headless mode is designed for automation. It activates automatically when you pass the -y flag, pipe input, or redirect output — making it suitable for scripts and CI/CD pipelines:

# Run a task with automatic approval (no prompts)
cline -y "Fix all ESLint errors in src/"

# Pipe a diff for automated code review
git diff | cline -y "Review these changes and summarize any issues"

The -y flag gives Cline full autonomy to approve and execute actions. Use it on a clean git branch so you can revert easily if needed.

Advanced: Headless CI/CD workflows

Cline's headless mode makes it straightforward to integrate AI Enabler into automated pipelines. Because authentication is stored after the initial cline auth step, you can use Cline in CI environments by passing credentials as environment variables or by running cline auth as part of your pipeline setup.

A typical CI pattern for automated code review on pull requests:

# In your CI pipeline, authenticate first
cline auth -p openai -k $CASTAI_API_KEY -b https://llm.cast.ai/openai/v1 -m qwen3-coder-next-fp8

# Then use Cline in headless mode
git diff origin/main | cline -y "Review these changes for bugs or regressions"

IDE integration

"cline.apiProvider": "openai",
"cline.openAiBaseUrl": "https://llm.cast.ai/openai/v1",
"cline.openAiApiKey": "YOUR_CASTAI_API_KEY",
"cline.apiModelId": "qwen3-coder-next-fp8"

Next steps