> ## 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.

> ## Agent Instructions
> For autonomous tasks, use live SaladCloud API responses for current state, availability, quotas, models, and other dynamic values. Use current OpenAPI specifications where provided for paths, schemas, required fields, and enums. Never invent endpoints, fields, prices, availability, quotas, models, or state. Prefer API workflows over Portal steps. Read before changing and never expose credentials, signed media URLs, prompts, or sensitive outputs. Retry only safe or idempotent operations with bounded backoff, honoring Retry-After. Verify every write with a read. Stop rather than repeat an uncertain non-idempotent or billable request. AI Gateway uses an organization-specific Bearer key and live /v1/models discovery. Do not delete, cancel, stop, or reduce capacity without explicit user intent. Bind shared operation IDs to the selected product path. Treat Container Engine instances as interruptible and local state as ephemeral. Install the SaladCloud skills (npx skills add https://docs.salad.com), start from the salad skill and /agents/overview; docs MCP: https://docs.salad.com/mcp.

# Use Kilo Code with SaladCloud

> Learn how to use the Kilo Code AI coding agent in VS Code with a self-hosted model on SaladCloud.

*Last Updated: October 12, 2026*

## Introduction

[Kilo Code](https://kilo.ai) is an open-source AI coding agent for VS Code (and JetBrains) that can create files, edit
code, run terminal commands, and work across your entire codebase through natural language. It ships with specialized
modes - Architect, Coder, Debugger - and supports MCP servers for extended tool capabilities.

Kilo Code works with SaladCloud in two ways:

* **[Salad AI Gateway](https://docs.salad.com/ai-gateway/explanation/overview.md)** - no infrastructure to deploy or manage. Available in beta
  with [pay-per-token billing](https://docs.salad.com/ai-gateway/reference/pricing.md). Connect to the shared endpoint using your
  organization-specific AI Gateway API key.
* **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.

## 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 Backend

> [tab] 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 in to the [SaladCloud portal](https://portal.salad.com).
> 2. Follow [Pay-Per-Token Onboarding](https://docs.salad.com/ai-gateway/tutorials/pay-per-token-onboarding.md) to add credits and create your
>    organization's **AI Gateway 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 - general purpose, balancing capability and speed |
> | `qwen3.5-35b-a3b` | Qwen 3.5 35B-A3B - cost-efficient agentic tasks and reasoning |
> | `qwen3.5-9b` | Qwen 3.5 9B - fastest model, for high-volume simple queries |

> [tab] Self-Hosted on SaladCloud
>
> First, deploy an OpenAI-compatible LLM server on SaladCloud.
>
> * 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 best fit for agentic coding is the Qwen3.6-35B-A3B (llama.cpp) recipe. On the recipe
>   page, 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.
>
> Available recipes:
>
> Ready-to-deploy recipes (best for less technical users):
>
> * [qwen3.6-35B-A3B](https://docs.salad.com/container-engine/reference/recipes/qwen3.6-35b-a3b-llama-cpp.md) - A powerful Mixture of Experts
>   model optimized for instruction-following tasks, ideal for agentic use cases.
> * [qwen3.5-9b-llama-cpp](https://docs.salad.com/container-engine/reference/recipes/qwen3.5-9b-llama-cpp.md) - Optimized for Qwen3.5 9B model.
>
> Recipes for custom deployments (best for advanced users):
>
> * [llama.cpp](https://docs.salad.com/container-engine/reference/recipes/llama-cpp.md) - Supports GGUF models
> * [sglang](https://docs.salad.com/container-engine/reference/recipes/sglang.md) - High-performance inference
> * [vllm](https://docs.salad.com/container-engine/reference/recipes/vllm.md) - Popular LLM serving framework
> * [ollama](https://docs.salad.com/container-engine/reference/recipes/ollama.md) - Simple model management
> * [tgi](https://docs.salad.com/container-engine/reference/recipes/tgi.md) - 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)

### Step 2: Install Kilo Code 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 **Kilo Code**
3. Click **Install** on the Kilo Code extension by Kilo-Org
4. Once installed, click the Kilo Code icon in the sidebar to open the panel

### Step 3: Configure Kilo Code to Use Your SaladCloud Endpoint

1. In the Kilo Code panel, click the **gear icon** to open provider settings
2. Click **Provider** and under `Custom Provider` click **Connect**
3. Set **Provider ID** and `Display Name` to something like `saladcloud`
4. Fill in the fields based on your chosen backend:

> [tab] Salad AI Gateway
>
> * **Base URL**: `https://ai.salad.cloud/v1`
> * **API Key**: your organization-specific AI Gateway API key
> * **Model ID**: e.g. `qwen3.6-35b-a3b`
>
> Use the AI Gateway key in the API Key field, not your account API key. No custom headers are needed.

> [tab] 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`) - authentication is handled via a custom header below
> * **Model ID**: the model name from your deployment (e.g., `qwen3.6-35b-a3b`)
>
> If your deployment has authentication enabled, expand **Custom Headers** and add:
>
> * Header name: `Salad-Api-Key`
> * Header value: your SaladCloud API key

### 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 Kilo Code successfully creates and runs the file, your setup is complete.

## Tips for Best Results

### Choose between plan/debug/code/ask modes based on your task:

* **Plan**: Best for high-level design and architecture tasks
* **Debug**: Ideal for fixing bugs and improving existing code
* **Code**: Great for generating new code and files
* **Ask**: Use for quick questions and explanations about your codebase

### Use Incremental Prompting for Complex Tasks

SaladCloud has a 100-second request timeout. For large multi-file tasks, break them into smaller steps and instruct Kilo
Code to save after each one:

> "Important: work incrementally. Create and save each file one at a time before moving on to the next."

### Model Recommendations

* **Qwen 3.6-35B-A3B**: Best balance of capability and cost for agentic coding tasks
* **Qwen 3.5-9B**: Suitable for simpler tasks; may struggle with complex multi-file edits


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.