MiniMax M1: open-weight hybrid-attention reasoning model with 1M context, 456B parameters, and an 80K-token thinking budget
Available on
Privacy
- ZDR
- Training
- No
- Region
- US
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.
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
MiniMax-M1-80k 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 | $0.55 | $2.20 | Input price |
MiniMax M1: open-weight hybrid-attention reasoning model with 1M context, 456B parameters, and an 80K-token thinking budget
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-compatibleAdd Opper as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
OpenAI-compatibleKilo Code's OpenAI-Compatible provider connects to Opper's gateway in two fields.
OpenAI-compatible