Skip to main content
Cursor is an AI-powered code editor. You can use it with Venice AI for private, uncensored access to a wide range of models.

Pay Per Token

No subscription. Pay only for what you use

All Models

Access Claude, GPT, DeepSeek, Llama, and more

OpenAI Compatible

Works via Venice’s OpenAI-compatible API

​
Setup

1

Get Your API Key

Generate a key from venice.ai/settings/api.
2

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
3

Add Models

In the model name field, type the Venice model ID and press Enter. Add each model you want to use. For example:See the model catalog for all available model IDs.
4

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.

​
The venice- Model Prefix

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.
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.

​
Resources

Venice API Docs

Full API reference

Model Catalog

Browse available models