Skip to main content
Use Modellix models inside Cursor by adding an OpenAI-compatible provider that targets the LLM gateway. Cursor talks Chat Completions-style APIs; Modellix exposes them at POST /v1/chat/completions.
Modellix media generation (image / video / speech) uses a different host and async task API. This page covers LLM text only (https://llm.modellix.ai).

​
Before you start

  1. Create a Modellix API key in the console.
  2. Pick a model ID in provider/name form (for example openai/gpt-5.5). See Models & Pricing for the full list.

​
Add an OpenAI-compatible provider

In Cursor settings, open the models / providers section and add a custom OpenAI-compatible (or equivalent override) endpoint: Cursor sends Authorization: Bearer <key>, which Modellix accepts. Include /v1 in the base URL so paths resolve to /v1/chat/completions.
If Cursor asks for a full chat completions URL instead of a base URL, use https://llm.modellix.ai/v1/chat/completions. Prefer base URL + model ID when the UI supports it.

​
Model ID tips

  • Prefer openai/... or google/... for the OpenAI-compatible path (same as OpenAI SDK).
  • anthropic/... can work on Chat Completions for many clients; for Anthropic-native tools use Messages instead (see Claude Code).
  • Browse available Model IDs and rates on Models & Pricing—do not assume bare upstream names without the provider/ prefix.

​
Optional: Anthropic-style override

If your Cursor build allows a separate Anthropic base URL override, use: Otherwise keep the OpenAI-compatible setup above for Chat Completions.

​
Troubleshooting