Cursor IDE

Route Cursor's AI features through LLMAI to access every supported model directly from your editor.

Model slugs in examples are illustrative. Confirm current availability in the live catalog and your account's /v1/models before use.

What This Does

Cursor is an AI-native code editor. By pointing it at LLMAI's endpoint, you gain access to every model in the LLMAI catalog — Kimi, DeepSeek, MiniMax, Qwen, MiMo, GLM, and Gemma — directly from Cursor's chat panel, inline edit, and code generation features. Token costs are drawn from your LLMAI balance the same as any other API call.

Setup

Step 1: Open the Settings File

Launch Cursor
Open the command palette: Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows / Linux)
Search for Open User Settings (JSON) and select it

Step 2: Add the LLMAI Configuration

Insert the following two fields into your settings.json:

{
  "cursor.general.openAIBaseURL": "https://api.llmai.dev/v1",
  "cursor.general.openAIAPIKey": "YOUR_LLMAI_API_KEY"
}

Retrieve your key from console.llmai.dev/keys.

Step 3: Configure via the UI (Alternative)

If you prefer the graphical settings panel:

Navigate to Cursor → Settings → Models
Find the API Key field and enter your LLMAI key
Find the Base URL or OpenAI API Base field and set it to https://api.llmai.dev/v1
Save; restart Cursor if prompted

Step 4: Pick Your Model

In Cursor's chat panel, type or select a model slug directly:

kimi-k2.7-code — best for code generation and refactoring
kimi-k2.6 — strong general reasoning
deepseek-v4-pro — optimised for code tasks
minimax-m3 — large context, multimodal
glm-5.3-flash — fast multimodal reasoning with a 1M-token context window

Recommended Models for Coding

Task	Recommended Model
Code generation & refactoring	`kimi-k2.7-code`
Code generation & review	`deepseek-v4-pro`
Explaining complex logic	`kimi-k2.6`
Working with large files	`minimax-m3`
Quick autocomplete	`gemini-3.1-flash-lite`
Budget-conscious coding	`gemma-4`

Troubleshooting

Cursor shows an authentication error

Double-check that the API key was pasted without extra spaces or line breaks
Verify the base URL is exactly https://api.llmai.dev/v1 (no trailing slash)

A model name is rejected

Use the slug exactly as listed in the Models reference — case matters
Avoid aliases or human-readable names; use the programmatic slug

Responses are slow

Switch to a lower-latency model such as gemini-3.1-flash-lite or glm-5.3-flash
Check your remaining balance at console.llmai.dev/billing

Notes

Cursor's UI layout may differ between versions. If you can't find a specific settings field, refer to Cursor's official documentation.
All of Cursor's AI features — chat, inline edits, tab completions — function through LLMAI.
Token usage is charged per interaction at the rate of whichever model is active.

On this page