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

# How to use Continue in Vs Code with SiliconFlow APIs

[Continue](https://www.continue.dev/) is an open-source AI code assistant for [VS Code](https://code.visualstudio.com/) and [JetBrains](https://www.jetbrains.com/) that keeps you in flow while you code: Ask questions about your codebase with [Chat](https://docs.continue.dev/ide-extensions/chat/quick-start), make targeted edits without switching context with [Edit](https://docs.continue.dev/ide-extensions/edit/quick-start), get inline suggestions as you type with [Autocomplete](https://docs.continue.dev/ide-extensions/autocomplete/quick-start), and hand off complex development tasks to [Agent ](https://docs.continue.dev/ide-extensions/agent/quick-start)— all without leaving your IDE.

By integrating SiliconFlow APIs into Continue, you can get access to [200+ open-source models](https://www.siliconflow.com/models), including frontier models like [DeepSeek V4 series](https://www.siliconflow.com/models/deepseek-v4-pro), [GLM-5.1](https://www.siliconflow.com/models/glm-5-1), and [Kimi K2.6](https://www.siliconflow.com/models/kimi-k2-6) — with cache support for faster and more cost-efficient inference. All accessible through one single API key.

This guide will walk you through connecting SiliconFlow to Continue in VS Code, from [obtaining your API key](https://cloud.siliconflow.com/) to configuring chat models, setting up Tab autocomplete, and verifying everything works end-to-end.

# **Step 1: Prerequisites**

## **Get Your SiliconFlow API Key**

Before you begin, ensure you have a valid SiliconFlow account:

* Register a SiliconFlow account at [https://cloud.siliconflow.com/](https://cloud.siliconflow.com/). You can sign up with Google or GitHub.
* Log in and navigate to `API Keys` in the dashboard.
* Click `🔑Create API Key `and add a name to your key to help you identify it later, then confirm to create it.
* Click the API key to copy it automatically.

⚠️ **Note:** Keep your API key secure; you will need it for the configuration in Step 3.

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue1.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=67f51d6d21c153dd3a30e3b7bde93399" alt="Continue1" width="2851" height="1647" data-path="images/continue1.png" />
</Frame>

# Step 2: Install Continue

Open VS Code, click the **Extensions** icon in the left Activity Bar (`Ctrl+Shift+X` / `Cmd+Shift+X`), search for **"Continue"**, and click **Install**.

> 💡 You can also open the extension page directly from the [Visual Studio Marketplace](https://marketplace.visualstudio.com/items?itemName=Continue.continue), clicking **Install** there will redirect you to VS Code, where you'll complete the installation the same way.

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue2.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=23e9dfb2325ebbb35c6bc2586e799b4c" alt="Continue2" width="2862" height="1814" data-path="images/continue2.png" />
</Frame>

# Step 3: Configure SiliconFlow APIs

Once Continue is installed, open the configuration file to set up your SiliconFlow models:

1. Click the **Continue icon** in the Activity Bar on the left
2. Click the **settings icon** in the top right corner of the Continue panel
3. In the left sidebar of settings, select **Config**
4. Click the settings icon next to **Local Config** and your `config.yaml` will open automatically

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue3.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=dd18ba4229ef3fceecc2053d73a370a5" alt="Continue3" width="2155" height="1388" data-path="images/continue3.png" />
</Frame>

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/contiue4.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=e2db4643c53dd323146412239154fd17" alt="Contiue4" width="2875" height="1748" data-path="images/contiue4.png" />
</Frame>

## Configure your chat models

Add your SiliconFlow models to the `models` list in `config.yaml`. You can configure multiple models and API keys in a single file. The example below sets up four models: `deepseek-ai/DeepSeek-V4-Flash`, `deepseek-ai/DeepSeek-V4-Pro`,` zai-org/GLM-5.1`,` moonshotai/Kimi-K2.6`.

```yaml theme={null}
name: Local Config
version: 1.0.0
schema: v1
models:
  - name: deepseek-ai/DeepSeek-V4-Flash
    provider: siliconflow
    model: deepseek-ai/DeepSeek-V4-Flash
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: deepseek-ai/DeepSeek-V4-Pro
    provider: siliconflow
    model: deepseek-ai/DeepSeek-V4-Pro
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: zai-org/GLM-5.1
    provider: siliconflow
    model: zai-org/GLM-5.1
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: moonshotai/Kimi-K2.6
    provider: siliconflow
    model: moonshotai/Kimi-K2.6
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
```

### **Not sure which model to pick?**

|                                 **Model**                                 |                      **Best for**                      |                                  **Key highlights**                                  |
| :-----------------------------------------------------------------------: | :----------------------------------------------------: | :----------------------------------------------------------------------------------: |
| [DeepSeek-V4-Flash](https://www.siliconflow.com/models/deepseek-v4-flash) |   Fast, cost-effective coding chat  / large codebase   |             1M context · 3 reasoning modes · best value in the V4 series             |
|   [DeepSeek-V4-Pro](https://www.siliconflow.com/models/deepseek-v4-pro)   |           Complex reasoning / large codebase           | 1M context · #1 open-source on math, STEM & competitive coding · approaches Opus 4.6 |
|           [GLM-5.1](https://www.siliconflow.com/models/glm-5-1)           |               Long-horizon agentic tasks               |      58.4 on SWE-Bench Pro · long-horizon execution · iterative self-improvement     |
|         [Kimi-K2.6](https://www.siliconflow.com/models/kimi-k2-6)         | Long-horizon tasks / Frontend generation / multi-agent |    Agent swarm architecture · long-horizon coding · prompt-to-frontend generation    |

### Cache More, Spend Less

All four models above are hosted on SiliconFlow with context caching enabled. SiliconFlow consistently delivers high cache hit rates across models — for example, according to [OpenRouter](https://openrouter.ai/)'s provider performance data, SiliconFlow achieves the highest cache hit rate among all GLM-5.1 providers at **88.6%**, significantly ahead of the competition. For you as a developer, this translates directly to faster response times and lower inference costs on repeated contexts.

Looking for more models? Browse the full model library at [SiliconFlow Models](https://siliconflow.com/models) or stay up to date with the latest releases on the [SiliconFlow Blog](https://siliconflow.com/blog).

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue5.jpg?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=8bea13ab3ccec1ee660ad9de15f76dc0" alt="Continue5" width="1280" height="945" data-path="images/continue5.jpg" />
</Frame>

## Configure Tab Autocomplete

To enable GitHub Copilot-style Tab completion, add the autocomplete model to your `models` list with `roles: - autocomplete`.

We recommend `Qwen/Qwen3-Coder-30B-A3B-Instruct` for its fast response time — as a MoE model that activates only 3B parameters per token, it delivers low-latency completions without sacrificing code quality.

```yaml theme={null}
  - name: Qwen/Qwen3-Coder-30B-A3B-Instruct
    provider: openai
    model: Qwen/Qwen3-Coder-30B-A3B-Instruct
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
    roles:
      - autocomplete
    autocompleteOptions:
      debounceDelay: 250
      maxPromptTokens: 1024
```

> **Note:** Avoid using large thinking-mode models for autocomplete — they generate more slowly and are not suited for real-time completion scenarios.

## Complete config.yaml Example

To get started quickly, replace your existing `config.yaml` with the full template below.

> **Note:** Replace all instances of `YOUR_SILICONFLOW_API_KEY` with your actual API key before saving.

```yaml theme={null}
name: Local Config
version: 1.0.0
schema: v1
models:
  - name: deepseek-ai/DeepSeek-V4-Flash
    provider: siliconflow
    model: deepseek-ai/DeepSeek-V4-Flash
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: deepseek-ai/DeepSeek-V4-Pro
    provider: siliconflow
    model: deepseek-ai/DeepSeek-V4-Pro
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: zai-org/GLM-5.1
    provider: siliconflow
    model: zai-org/GLM-5.1
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: moonshotai/Kimi-K2.6
    provider: siliconflow
    model: moonshotai/Kimi-K2.6
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
  - name: Qwen/Qwen3-Coder-30B-A3B-Instruct
    provider: openai
    model: Qwen/Qwen3-Coder-30B-A3B-Instruct
    apiKey: "YOUR_SILICONFLOW_API_KEY"
    apiBase: "https://api.siliconflow.com/v1"
    roles:
      - autocomplete
    autocompleteOptions:
      debounceDelay: 250
      maxPromptTokens: 1024
```

# Step 4: Verify Your Setup

1. **Save and reload**

Save `config.yaml`. Continue reloads configuration automatically in most cases. If changes don't take effect, restart your IDE.

2. **Test chat**

Open the Continue chat panel. All models defined in your config will appear in the model selector — pick any one, send a test message such as `"Hello"`, and confirm you receive a response.

3. **Test autocomplete**

Open any code file (e.g., a Python file), type a snippet like`def quick_sort(arr):`, and pause for a moment. If a grey inline suggestion appears after your cursor, Tab autocomplete is working correctly.

# **Already Using OpenRouter?**

If you already have an OpenRouter account, you can connect your SiliconFlow API key via BYOK.

Once connected:

* Requests draw from your SiliconFlow balance first
* Billing and rate limits stay in your SiliconFlow account
* OpenRouter's fallback routing still works to improve reliability

**Bonus:** OpenRouter waives platform fees on your first 1M BYOK requests per month.

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue6.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=fd81a87768179809e9225786fead85b0" alt="Continue6" width="1280" height="719" data-path="images/continue6.png" />
</Frame>

To set it up in Continue with OpenRouter API Keys:

1. Open the Continue panel and click the **settings icon** in the top right corner
2. In the left sidebar, select **Models**
3. Click the `+` icon next to Models
4. Select **OpenRouter** as the provider
5. Choose your desired model and enter your **OpenRouter API key**

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue7.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=fc2c67f62991d3dc2a6d66ec1755f258" alt="Continue7" width="1280" height="841" data-path="images/continue7.png" />
</Frame>

<Frame>
  <img src="https://mintcdn.com/siliconflowcom/OT0rK2iHgnGtmugf/images/continue8.png?fit=max&auto=format&n=OT0rK2iHgnGtmugf&q=85&s=24962c4f2fe2c44aea2198194d22df68" alt="Continue8" width="970" height="1005" data-path="images/continue8.png" />
</Frame>

# Resources

### **Continue**

* Website: [https://continue.dev/](https://continue.dev/)
* Docs: [https://docs.continue.dev/](https://docs.continue.dev/)
* Github: [https://github.com/continuedev/continue](https://github.com/continuedev/continue)

### OpenRouter

* BYOK Setting: [https://openrouter.ai/workspaces/default/byok](https://openrouter.ai/workspaces/default/byok)
* SiliconFlow on OpenRouter: [https://openrouter.ai/provider/siliconflow](https://openrouter.ai/provider/siliconflow)

### **SiliconFlow**

* Website: [https://siliconflow.com](https://siliconflow.com)
* API Documentation: [https://docs.siliconflow.com](https://docs.siliconflow.com)
* Model Library: [https://siliconflow.com/models](https://siliconflow.com/models)
* Discord: [https://discord.com/invite/7Ey3dVNFpT](https://discord.com/invite/7Ey3dVNFpT)
* X: [https://x.com/SiliconFlowAI](https://x.com/SiliconFlowAI)