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

# Use SinarCloud in VS Code

> Compare the VS Code coding agents that run on SinarCloud models, and open the guide for the one you use.

Several coding agents for VS Code can run on SinarCloud models. Each one takes the base URL and your API key in its own settings, and none of them needs an account with the extension's maker. Pick the one you prefer, then follow its guide.

| Extension | Where you connect it | Base URL | Guide |
| - | - | - | - |
| Claude Code for VS Code | VS Code's user settings | `https://ai.sinarcloud.com` | [Claude Code in VS Code](https://docs.sinarcloud.com/integrations/claude-code.md#use-claude-code-in-vs-code) |
| Cline | **OpenAI Compatible** in Cline's settings | `https://ai.sinarcloud.com/v1` | [Cline](https://docs.sinarcloud.com/integrations/cline.md) |
| Kilo Code | **Custom provider** in Kilo Code's settings | `https://ai.sinarcloud.com/v1` | [Kilo Code](https://docs.sinarcloud.com/integrations/kilo-code.md) |
| Continue | A model entry in Continue's `config.yaml` | `https://ai.sinarcloud.com/v1` | [Continue](https://docs.sinarcloud.com/integrations/continue.md) |

Claude Code uses the Anthropic Messages format. The other three use the OpenAI Chat Completions format. Both formats use the same API key, models, and balance. See [Compatibility](https://docs.sinarcloud.com/integrations/compatibility.md).

## Before you start

* Get an API key and a model alias as described in [Before you connect](https://docs.sinarcloud.com/integrations/before-you-connect.md).
* Create a separate API key for each extension. The **Usage** page can then show what each one spends, and you can revoke one key without breaking the others.
* Choose a model whose **Model capabilities** list **Chat completions**, **Tool use**, and **Streaming**.

## What all of them have in common

* **Each step is a request.** An agent sends a new request for every step of a task, and each one includes the conversation so far. Start a new task or session for each new piece of work.
* **Their cost displays aren't your charges.** The extensions estimate costs in their own way, or show only tokens. To see what you spent, open **AI** > **Usage** in the console and filter by the extension's API key.
* **Output limits must fit the model.** If you set a maximum output in the extension, keep it at or below the model's **Maximum output (tokens)**. Otherwise SinarCloud refuses the request with "The output-token limit exceeds the model's allowed range."

## Guides

> [card] [Claude Code for VS Code](https://docs.sinarcloud.com/integrations/claude-code.md#use-claude-code-in-vs-code)
>
> Anthropic's coding agent in a panel next to your code.

> [card] [Cline](https://docs.sinarcloud.com/integrations/cline.md)
>
> Connect with Cline's OpenAI Compatible settings.

> [card] [Kilo Code](https://docs.sinarcloud.com/integrations/kilo-code.md)
>
> Connect with Kilo Code's Custom provider form.

> [card] [Continue](https://docs.sinarcloud.com/integrations/continue.md)
>
> Add a SinarCloud model to Continue's config file.


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