> ## 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 Continue with SaladCloud

> Learn how to use the Continue AI coding assistant in VS Code or JetBrains with a self-hosted model on SaladCloud.

*Last Updated: May 18, 2026*

## Introduction

[Continue](https://continue.dev) is an open-source AI coding assistant for VS Code and JetBrains. Unlike pure agentic
tools, Continue focuses on the full coding workflow: autocomplete, inline chat, codebase-aware Q\&A, and multi-file
edits. Supports any OpenAI-compatible endpoint with custom headers.

Continue works with SaladCloud in two ways:

* **[Salad AI Gateway](/ai-gateway/explanation/overview)** - no infrastructure to deploy or manage. Sign up for access,
  point Continue at a single shared endpoint, and use your Salad API key directly. Currently in closed beta with monthly
  flat-rate access.
* **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](https://portal.salad.com)
* VS Code or JetBrains IDE installed

## Step-by-Step Setup

### Step 1: Choose Your 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">
    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 Qwen3.6-35B-A3B (llama.cpp) recipe works well for coding assistance. 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](/container-engine/reference/recipes/qwen3.6-35b-a3b-llama-cpp) - A powerful Mixture of Experts
      model optimized for instruction-following tasks.
    * [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 Continue

**VS Code:**

1. Open the Extensions view (`Ctrl+Shift+X` or `Cmd+Shift+X`)
2. Search for **Continue**
3. Click **Install** on the Continue extension by Continue Dev
4. Once installed, click the Continue icon in the sidebar

**JetBrains:**

Install the Continue plugin from the JetBrains Marketplace via **Settings → Plugins → Marketplace**.

### Step 3: Configure Continue to Use Your SaladCloud Endpoint

Continue is configured via `~/.continue/config.yaml`. Open it from the Continue panel by clicking the gear icon, or edit
it directly. The configuration UI does not currently support all necessary fields, so you will need to add the model
config manually in the YAML file.

<Tabs>
  <Tab title="Salad AI Gateway">
    Add your AI Gateway model:

    ```yaml theme={null}
    models:
      - name: Salad AI Gateway
        provider: openai
        model: qwen3.6-35b-a3b
        apiBase: https://ai.salad.cloud/v1
        apiKey: your-salad-api-key
    ```

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

  <Tab title="Self-Hosted on SaladCloud">
    Add your SaladCloud deployment as a model:

    ```yaml theme={null}
    models:
      - name: SaladCloud Qwen 3.6
        provider: openai
        model: qwen3.6-35b-a3b
        apiBase: https://your-endpoint.salad.cloud/v1
        apiKey: dummy
        requestOptions:
          headers:
            Salad-Api-Key: your-salad-api-key
    ```

    Replace `https://your-endpoint.salad.cloud/v1` with your actual endpoint URL.

    If your deployment does not require authentication, omit the `requestOptions` section entirely and set `apiKey` to
    any non-empty string.

    To also use your SaladCloud model for **autocomplete**, add :

    ```yaml theme={null}
    roles:
      - autocomplete
    ```
  </Tab>
</Tabs>

### Step 4: Test the Connection

Reload VS Code (`Ctrl+Shift+P` → **Reload Window**), then open the Continue chat panel and ask:

> "Summarize what this project does in one sentence."

If Continue responds, your setup is complete.

## Tips for Best Results

### Set Context Window

Add `contextLength` to your model config to help Continue manage prompt sizes correctly:

```yaml theme={null}
models:
  - name: SaladCloud Qwen 3.6
    provider: openai
    model: qwen3.6-35b-a3b
    apiBase: https://your-endpoint.salad.cloud/v1
    apiKey: dummy
    roles:
      - chat
      - autocomplete
    contextLength: 262144
    requestOptions:
      headers:
        Salad-Api-Key: your-salad-api-key
```

The Qwen 3.6-35B-A3B recipe supports up to 262,144 tokens.

### Handle Autocomplete Timeouts

SaladCloud has a 100-second request timeout. Autocomplete requests are short and typically complete well within this
limit, but for large context windows, consider setting a shorter `maxTokens` for autocomplete to reduce latency:

```yaml theme={null}
tabAutocompleteModel:
  name: SaladCloud Qwen 3.6
  provider: openai
  model: qwen3.6-35b-a3b
  apiBase: https://your-endpoint.salad.cloud/v1
  apiKey: dummy
  defaultCompletionOptions:
    maxTokens: 512
  requestOptions:
    headers:
      Salad-Api-Key: your-salad-api-key
```

### Model Recommendations

* **Qwen 3.6-35B-A3B**: Best for chat, codebase Q\&A, and multi-file edits
* **Qwen 3.5-9B**: Fast enough for autocomplete; good balance of latency and quality