LLMsRelay is an independently operated API gateway. It is not affiliated with or endorsed by Anthropic, PBC. Product and model names are used only to describe compatibility.

Setup

Open Cursor → Settings → Models
Click Add Provider
Set Base URL to https://api.llmsrelay.com/v1
Enter your LLMsRelay API Key
Add the model IDs you want to use (e.g., claude-sonnet-4.6)
Select the model from the model picker in the chat panel

Recommended Models

claude-opus-5 / claude-fable-5 — highest-capability options for complex tasks
claude-opus-4.8 / claude-opus-4.7 — long coding and reasoning sessions
claude-sonnet-5 / claude-sonnet-4.6 — balanced coding defaults
claude-haiku-4.5 — Fastest, ideal for autocomplete

Troubleshooting

Ensure the base URL ends with /v1
Verify your API key is correct and has sufficient credits
Check that the model ID matches exactly (e.g., claude-sonnet-4.6, not claude-3-sonnet)

Windows setup

Install Cursor for Windows from cursor.sh (the installer adds cursor to your PATH automatically).
Open Settings with Ctrl+, → Models.
Toggle OpenAI API Key, paste your sk-cs4-... key.
Toggle Override OpenAI Base URL, set https://api.llmsrelay.com/v1.
Click Verify, then add model IDs returned by GET /v1/models.

Behind a corporate proxy? Set Windows-wide proxy via setx HTTPS_PROXY "http://proxy.company:8080" in PowerShell, then restart Cursor.

Tab completion uses Cursor's own model and is not affected by these settings — only Chat / Composer / Agent route through LLMsRelay.

Ready to start?

Create a key and configure a compatible API route in under 2 minutes.

View Plans