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 Cline on Llama 4 Maverick 17B 128E Instruct
Cline is an open-source autonomous coding agent for VS Code. It plans and applies multi-file changes, runs terminal commands, and works with any OpenAI-compatible provider, with its source on GitHub under Apache-2.0. Point its OpenAI-Compatible provider at Opper's base URL to run it on any of 700+ models, with fallbacks and a choice of region built in.
RunClineonin
ClineoninConnect Cline 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
Cursor
Point Cursor's OpenAI base URL at Opper to run it on any of 700+ models.
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