> ## 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.

# Cursor IDE

> Configure Cursor IDE to use Venice models including Claude, GPT, DeepSeek, and Qwen via an OpenAI-compatible base URL and the venice- model prefix.

[Cursor](https://www.cursor.com/) is an AI-powered code editor. You can use it with Venice AI for private, uncensored access to a wide range of models.

<CardGroup cols={3}>
  <Card title="Pay Per Token" icon="coins">
    No subscription. Pay only for what you use
  </Card>

  <Card title="All Models" icon="microchip">
    Access Claude, GPT, DeepSeek, Llama, and more
  </Card>

  <Card title="OpenAI Compatible" icon="plug">
    Works via Venice's OpenAI-compatible API
  </Card>
</CardGroup>

***

## Setup

<Steps>
  <Step title="Get Your API Key">
    Generate a key from [venice.ai/settings/api](https://venice.ai/settings/api).
  </Step>

  <Step title="Configure Cursor">
    Open **Cursor Settings** (gear icon), scroll to **Models** and click **Add Model**.

    Under **OpenAI Compatible**, enter:

    * **Override OpenAI Base URL**: `https://api.venice.ai/api/v1`
    * **OpenAI API Key**: Your Venice API key
  </Step>

  <Step title="Add Models">
    In the model name field, type the Venice model ID and press Enter. Add each model you want to use. For example:

    * `minimax-m25`
    * `kimi-k2-5`
    * `venice-claude-opus-4-6` (see [prefix note below](#the-venice--model-prefix))

    See the [model catalog](/models/text) for all available model IDs.
  </Step>

  <Step title="Select and Verify">
    Open a new chat and use the **model selector at the bottom of the chat** to pick one of the Venice models you just added. Send a test message. If you get a response, you're all set.
  </Step>
</Steps>

***

## The `venice-` Model Prefix

<Warning>
  **Claude models require the `venice-` prefix when used in Cursor.**

  Cursor rewrites requests for `claude-*` models into Anthropic's native format, which is incompatible with Venice. Prefixing the model ID with `venice-` prevents this rewrite. Venice strips the prefix automatically.
</Warning>

| Model                | Standard ID            | Cursor ID                     |
| -------------------- | ---------------------- | ----------------------------- |
| Claude Opus 4.6      | `claude-opus-4-6`      | `venice-claude-opus-4-6`      |
| Claude Opus 4.6 Fast | `claude-opus-4-6-fast` | `venice-claude-opus-4-6-fast` |
| Claude Sonnet 4.6    | `claude-sonnet-4-6`    | `venice-claude-sonnet-4-6`    |
| Claude Opus 4.5      | `claude-opus-4-5`      | `venice-claude-opus-4-5`      |
| Claude Sonnet 4.5    | `claude-sonnet-4-5`    | `venice-claude-sonnet-4-5`    |

<Info>
  Non-Claude models (e.g. `minimax-m25`, `kimi-k2-5`, `zai-org-glm-5`) are **not affected** and work without the prefix. The `venice-` prefix is safe to use on any model since Venice always strips it, but it is only required for Claude models in Cursor.
</Info>

***

## Resources

<CardGroup cols={2}>
  <Card title="Venice API Docs" icon="book" href="/api-reference/api-spec">
    Full API reference
  </Card>

  <Card title="Model Catalog" icon="list" href="/models/text">
    Browse available models
  </Card>
</CardGroup>