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

# Cline

> Configure the Cline coding assistant in VS Code to use private Venice models through an OpenAI-compatible API provider.

[Cline](https://cline.bot/) is an AI coding assistant for VS Code that can read and edit files, run commands, and work through multi-step development tasks. Venice works through Cline's OpenAI-compatible provider settings.

<CardGroup cols={3}>
  <Card title="VS Code Integration" icon="code">
    Use Venice models without leaving your editor
  </Card>

  <Card title="OpenAI Compatible" icon="plug">
    Connect through Venice's `/chat/completions` endpoint
  </Card>

  <Card title="Model Flexibility" icon="microchip">
    Choose any compatible Venice text model
  </Card>
</CardGroup>

***

## Prerequisites

* A Venice API key from [venice.ai/settings/api](https://venice.ai/settings/api)
* [Visual Studio Code](https://code.visualstudio.com/) installed
* The [Cline extension](https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev) installed in VS Code

***

## Setup

<Steps>
  <Step title="Open Cline settings">
    Select the Cline icon in the VS Code activity bar, then select the gear icon to open Cline's settings.
  </Step>

  <Step title="Choose the API provider">
    Set **API Provider** to **OpenAI Compatible**.
  </Step>

  <Step title="Configure Venice">
    Enter the following values:

    | Setting  | Value                                                  |
    | -------- | ------------------------------------------------------ |
    | Base URL | `https://api.venice.ai/api/v1`                         |
    | API Key  | Your Venice API key                                    |
    | Model ID | A model ID from the [text model catalog](/models/text) |

    For example, use `zai-org-glm-5-1` as the Model ID.

    Enter the API key itself, without a `Bearer` prefix. Keep the Base URL at `/api/v1`; Cline adds the `/chat/completions` path.
  </Step>

  <Step title="Configure model capabilities">
    Expand **Model Configuration** and set the context window and maximum output tokens to match the selected model. Enable the capabilities that the model supports, including image input or computer use when applicable.

    Check the selected model in the [text model catalog](/models/text) before enabling optional capabilities.
  </Step>

  <Step title="Save and test">
    Save the provider settings, open a project, and give Cline a small task such as:

    ```txt theme={"system"}
    Review the current file and suggest one safe improvement.
    ```

    Review each file or command permission before approving it.
  </Step>
</Steps>

***

## Verify the Venice API

If Cline cannot connect, confirm the API key and available model IDs independently:

```bash theme={"system"}
curl https://api.venice.ai/api/v1/models \
  -H "Authorization: Bearer $VENICE_API_KEY"
```

Copy a model's `id` exactly into Cline's **Model ID** field.

***

## Configuration Notes

* Use `https://api.venice.ai/api/v1` as the Base URL, not the full `/chat/completions` endpoint.
* Model IDs can change over time. Use the [text model catalog](/models/text) or `GET /models` instead of relying on an older example.
* Cline's context-window and output-token settings affect how it budgets requests. Match them to the selected model for the best results.
* Keep your Venice API key private. Do not paste it into source files or commit it to git.

***

## Troubleshooting

<AccordionGroup>
  <Accordion title="401 or authentication error">
    Confirm that the API key comes from [venice.ai/settings/api](https://venice.ai/settings/api). Paste the raw key into Cline without `Bearer` or extra whitespace.
  </Accordion>

  <Accordion title="Model not found">
    Confirm that the Model ID appears in the [text model catalog](/models/text) or the response from `GET /models`, then copy it exactly.
  </Accordion>

  <Accordion title="Connection or endpoint error">
    Confirm that **API Provider** is **OpenAI Compatible** and the Base URL is exactly `https://api.venice.ai/api/v1`.
  </Accordion>

  <Accordion title="Cline cannot use tools or edit files">
    Open **Model Configuration**, confirm that the selected model supports the required capabilities, and enable computer use if Cline exposes that option for the model.
  </Accordion>
</AccordionGroup>

***

## Resources

<CardGroup cols={2}>
  <Card title="Original Venice Cline Guide" icon="book" href="https://venice.ai/blog/how-to-use-the-venice-api-with-cline-in-vscode-a-developers-guide">
    Read the canonical Venice article
  </Card>

  <Card title="Venice Text Models" icon="list" href="/models/text">
    Browse available Venice model IDs
  </Card>

  <Card title="Cline Provider Docs" icon="gear" href="https://docs.cline.bot/provider-config/openai-compatible">
    OpenAI-compatible provider settings
  </Card>

  <Card title="Venice API Reference" icon="code" href="/api-reference/api-spec">
    Full endpoint and parameter docs
  </Card>
</CardGroup>
