Use Aider with SaladCloud

Learn how to use the Aider AI coding agent from the command line with a self-hosted model on SaladCloud.

Last Updated: April 3, 2026

Introduction

Aider is an open-source AI pair programmer that runs in your terminal. It integrates with your local git repository, can create and edit files across multiple languages, and commits changes automatically as you work. Aider is designed from the ground up to support OpenAI-compatible endpoints, making it one of the simplest tools to connect to a model on SaladCloud.

Aider works with SaladCloud in two ways:

• Salad AI Gateway - no infrastructure to deploy or manage. Sign up for access, point Aider at a single shared endpoint, and use your Salad API key directly. Currently in closed beta, available via monthly subscription.
• Self-hosted model - deploy your own SaladCloud container group, billed per hour, 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
• Python 3.8+ installed
• A local git repository to work in

Step-by-Step Setup

Step 1: Choose Your Backend

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.
2. Once approved, find your Salad API key in the portal.

Available models:

Model	Description
qwen3.5-35b-a3b	Qwen 3.5 35B Mixture of Experts - best for agentic tasks and complex reasoning
qwen3.5-27b	Qwen 3.5 27B - strong balance of capability and speed
qwen3.5-9b	Qwen 3.5 9B - fastest response times, suited for lighter tasks

Self-Hosted on SaladCloud

First, deploy an OpenAI-compatible LLM server on SaladCloud.

• Go to the SaladCloud portal 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 Qwen3.5-35B-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):

• qwen3.5-35B-A3B — A powerful Mixture of Experts model optimized for instruction-following tasks, ideal for agentic use cases.
• qwen3.5-9b-llama-cpp — Optimized for Qwen3.5 9B model.

Recipes for custom deployments (best for advanced users):

• llama.cpp — Supports GGUF models
• sglang — High-performance inference
• vllm — Popular LLM serving framework
• ollama — Simple model management
• tgi — Hugging Face Text Generation Inference server

After deployment, note your:

• API endpoint URL (e.g., https://your-endpoint.salad.cloud)

Step 2: Install Aider on your local machine

Install Aider via pip:

pip install aider-chat

Verify the installation:

aider --version

Step 3: Configure Aider to Use Your SaladCloud Endpoint

Salad AI Gateway

Set the required environment variables before running Aider:

export OPENAI_API_BASE=https://ai.salad.cloud:40404/v1
export OPENAI_API_KEY=your-salad-api-key

No custom headers are needed - your Salad API key in OPENAI_API_KEY is all that’s required.

Self-Hosted on SaladCloud

Set the required environment variables before running Aider:

export OPENAI_API_BASE=https://your-endpoint.salad.cloud/v1
export OPENAI_API_KEY=dummy

OPENAI_API_KEY is required, but can be set to any non-empty string (e.g., dummy).

Alternatively, create a .aider.conf.yml file in your project root to persist the configuration:

model: openai/qwen3.5-35b-a3b
openai-api-base: https://your-endpoint.salad.cloud/
openai-api-key: your-salad-api-key

If your SaladCloud deployment requires authentication, create .aider.model.settings.yml file and add the following header configuration:

- name: openai/qwen3.5-35b-a3b
  extra_params:
    extra_headers:
      Salad-Api-Key: your-salad-api-key

Step 4: Start Aider and Test the Connection

Navigate to your project directory and start Aider, prefixing the model name with openai/:

cd /path/to/your/project
aider --model openai/qwen3.5-35b-a3b

The openai/ prefix is important — it tells Aider to route through the OpenAI-compatible provider.

Test with a simple task:

“Create a hello world Python script that prints ‘Hello from SaladCloud!’”

If Aider successfully creates and commits the file, your setup is complete.

Note: Aider may display a warning about an unknown model. This is safe to ignore — Aider is simply checking its internal model database and your SaladCloud model won’t be listed there.

Tips for Best Results

Use the --edit-format Flag

For smaller or less capable models, the whole edit format is more reliable than the default diff format:

aider --model openai/qwen3.5-35b-a3b --edit-format whole

The diff format produces more efficient edits but requires the model to generate valid unified diffs, which some models struggle with.

Work in a Git Repository

Aider is designed to work inside a git repository. It automatically commits each change it makes, giving you a full undo history. Initialize git in your project if you haven’t already:

git init

Set a Context Window

When using a custom deployment, ensure your model server is configured with a sufficient context window. Aider works best with at least 16384 tokens, ideally 32768 or higher. Our preconfigured Qwen 3.5-35B-A3B recipe already has optimal settings.

Model Recommendations

• Qwen 3.5-35B-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 page was created using Aider powered by an LLM model running on SaladCloud.