Cursor is the AI-native code editor from Anysphere, built on top of VS Code. It brings inline edits, codebase-aware chat, and agentic multi-file changes into the editor, and it lets you bring your own model by overriding its OpenAI base URL. Point that base URL at Opper's compatible gateway and you can drive Cursor with any model in the catalogue, with a choice of region and zero data retention.
CursoroninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Gemini 3.1 Flash Lite Image runs on the routes below. Route only to EU providers when your data has to stay in Europe.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|
| US | No | $0.25 | $1.50 | Input price | ||
| Multi | No | $0.25 | $1.50 | Input price |
Gemini 3.1 Flash Lite Image is Google's fastest image model, generating and editing 1K visuals in about four seconds for high-throughput pipelines.
Step-by-step setup for running Cursor on each of these models through Opper.
Cline's OpenAI-Compatible provider points straight at Opper's gateway.
OpenAI-compatible
Add Opper as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
OpenAI-compatible
Kilo Code's OpenAI-Compatible provider connects to Opper's gateway in two fields.
OpenAI-compatible