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

# Use Cline with SaladCloud

> Learn how to use the Cline AI coding agent with SaladCloud for AI-powered development.

*Last Updated: May 18, 2026*

## Introduction

[Cline](https://github.com/cline/cline) is an open-source AI coding agent for VS Code that can create files, edit code,
run terminal commands, execute bash commands, and more. It acts as an autonomous pair programmer that helps you build
applications through natural language conversations.

Cline works with SaladCloud in two ways:

* **[Salad AI Gateway](/ai-gateway/explanation/overview)** - no infrastructure to deploy or manage. Sign up for access,
  point Cline at a single shared endpoint, and use your Salad API key directly. Currently in closed beta.
* **Self-hosted model** - deploy your own SaladCloud container group for full control over the model, hardware, and
  configuration. Still very easy to set up and use.

Self-hosted models are billed per hour. Salad AI Gateway is available via monthly flat-rate access during the closed
beta period.

For real-world examples of building applications with Cline and SaladCloud, check out our blog post:
[Use Cline with SaladCloud: Building Real Apps for Under \$0.01](https://blog.salad.com/use-cline-with-saladcloud-building-real-apps-for-under-1-cent/)

## Prerequisites

Before getting started, make sure you have:

* A [SaladCloud account](https://portal.salad.com)
* VS Code installed on your machine

## Step-by-Step Setup

### Step 1: Choose Your Salad Backend

<Tabs>
  <Tab title="Salad AI Gateway">
    Salad AI Gateway is the fastest way to get started - no container groups to deploy, no cold starts to wait for.

    1. Sign up for early access at [salad.com/ai-gateway](https://salad.com/ai-gateway).
    2. Once approved, find your **Salad API key** in the [portal](https://portal.salad.com/api-key).

    Available models:

    | Model             | Description                                                              |
    | :---------------- | :----------------------------------------------------------------------- |
    | `qwen3.6-35b-a3b` | Qwen 3.6 35B-A3B - best for agentic tasks, coding, and complex reasoning |
    | `qwen3.6-27b`     | Qwen 3.6 27B - strong balance of capability and speed                    |
    | `qwen3.5-9b`      | Qwen 3.5 9B - fastest response times, suited for lighter tasks           |
  </Tab>

  <Tab title="Self-Hosted on SaladCloud">
    Deploy your own OpenAI-compatible LLM server on SaladCloud Container Engine.

    * Go to the [SaladCloud portal](https://portal.salad.com) and create an account if you do not already have one.
    * Create an organization or choose an existing one, then click "Deploy a container group".
    * Select an LLM recipe. The Qwen3.6-35B-A3B (llama.cpp) recipe is the best fit for agentic use cases. Provide a
      name and deploy - the rest is preconfigured with recommended settings.
    * Once deployed, your endpoint will be live and serving an OpenAI-compatible API.

    Ready-to-deploy recipes (best for less technical users):

    * [qwen3.6-35B-A3B](/container-engine/reference/recipes/qwen3.6-35b-a3b-llama-cpp) - A powerful Mixture of Experts
      model optimized for instruction-following tasks, ideal for agentic use cases.
    * [qwen3.5-9b-llama-cpp](/container-engine/reference/recipes/qwen3.5-9b-llama-cpp) - Optimized for Qwen3.5 9B model.

    Recipes for custom deployments (best for advanced users):

    * [llama.cpp](/container-engine/reference/recipes/llama-cpp) - Supports GGUF models
    * [sglang](/container-engine/reference/recipes/sglang) - High-performance inference
    * [vllm](/container-engine/reference/recipes/vllm) - Popular LLM serving framework
    * [ollama](/container-engine/reference/recipes/ollama) - Simple model management
    * [tgi](/container-engine/reference/recipes/tgi) - Hugging Face Text Generation Inference server

    After deployment, note your:

    * **API endpoint URL** (e.g., `https://your-endpoint.salad.cloud`)
    * **API key** (from your SaladCloud organization settings, if you enabled authentication)
  </Tab>
</Tabs>

### Step 2: Install Cline in VS Code

1. Open VS Code and go to the Extensions view (`Ctrl+Shift+X` or `Cmd+Shift+X` on macOS)
2. Search for "Cline" or use the extension ID: `saoudrizwan.claude-dev`
3. Click **Install** on the Cline extension
4. Once installed, click the Cline icon in the sidebar to open the Cline panel

### Step 3: Configure Cline

1. In the Cline sidebar, click the **gear icon** (⚙️) to open settings
2. Set **API Provider** to `OpenAI Compatible`
3. Fill in the fields based on your chosen backend:

<Tabs>
  <Tab title="Salad AI Gateway">
    * **Base URL**: `https://ai.salad.cloud/v1`
    * **API Key**: your Salad API key
    * **Model ID**: e.g. `qwen3.6-35b-a3b`

    No custom headers are needed - your Salad API key in the API Key field is all that's required.
  </Tab>

  <Tab title="Self-Hosted on SaladCloud">
    * **Base URL**: your SaladCloud endpoint URL (e.g., `https://your-endpoint.salad.cloud/v1`)
    * **API Key**: any non-empty string (e.g., `dummy`)
    * **Model ID**: the model name from your deployment (e.g., `qwen3.6-35b-a3b`)

    If you enabled authentication on your SaladCloud deployment, add a custom header:

    * Header name: `Salad-Api-Key`
    * Header value: your Salad API key
  </Tab>
</Tabs>

**Pro tip:** Cline supports separate models for Plan and Act modes. You can use a frontier model for planning and your
SaladCloud model for execution, or use the same model for both. A 35B model handles both planning and acting
effectively.

### Step 4: Test the Connection

Start with a simple task to verify everything is working:

> "Create a hello world Python script that prints 'Hello from SaladCloud!'"

If Cline successfully creates and runs the file, your setup is complete.

## Tips for Best Results

### Use Incremental Prompting for Complex Tasks

When working on long agentic sessions, tell Cline to work in small steps and save after each one:

> "Important: Work incrementally. Do NOT try to write all files at once. Break this into small steps, create and save
> each file one at a time, and make sure each step works before moving on."

This reduces the chance of interrupted generations, makes it easier to recover from errors, and helps maintain context
across multiple interactions.

### Set a Generous Context Window

For self-hosted deployments, configure your LLM server with a context window of at least **16384 tokens**, ideally
**32768** or higher. The preconfigured recipes (e.g., Qwen 3.6-35B-A3B) already have optimal context window settings. AI
Gateway models support up to 262,144 tokens.

### Model Recommendations

* **Qwen 3.6-35B-A3B**: Best for complex agentic tasks - excellent balance of capability and cost
* **Qwen 3.5-9B**: Good for lighter tasks and faster response times

***

<Callout variation="note">
  This documentation page was created using Cline powered by an LLM model running on SaladCloud.
</Callout>