Cursor IDE

Route Cursor's AI features through LLM247 to access every supported model directly from your editor.

What This Does

Cursor is an AI-native code editor. By pointing it at LLM247's endpoint, you gain access to every model in the LLM247 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 LLM247 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 LLM247 Configuration

Insert the following two fields into your settings.json:

{
  "cursor.general.openAIBaseURL": "https://api.llm247.net/v1",
  "cursor.general.openAIAPIKey": "YOUR_LLM247_API_KEY"
}

Retrieve your key from llm247.net/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 LLM247 key
Find the Base URL or OpenAI API Base field and set it to https://api.llm247.net/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-5.1 — fast responses, low latency

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.llm247.net/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-5.1
Check your remaining balance at llm247.net/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 LLM247.
Token usage is charged per interaction at the rate of whichever model is active.

On this page