Llama 4 Maverick at bf16 on SCX's Australian SambaNova deployment, served at a 128K window (the weights support 1M).
Available on
Pricing from$1.13/ 1M input$3.44/ 1M output131Kcontext
Privacy
- ZDR
- Training
- No
- Region
- Australia
Run Cursor on Llama 4 Maverick 17B 128E Instruct
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.
RunCursoronin
CursoroninConnect Cursor to Llama 4 Maverick 17B 128E Instruct
Set up with agents
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Where you can run it
Llama 4 Maverick 17B 128E Instruct 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 |
|---|---|---|---|---|---|
| SCX | Australia | No | $1.13 | $3.44 |
The model
More apps on Opper
Cline
Cline's OpenAI-Compatible provider points straight at Opper's gateway.
Editors
OpenAI-compatible
Continue
Add Opper as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
Editors
OpenAI-compatible
Kilo Code
Kilo Code's OpenAI-Compatible provider connects to Opper's gateway in two fields.
Editors
OpenAI-compatible