Codex is OpenAI's open-source coding agent for the terminal. It works from natural-language instructions to edit code across your project, run commands, and complete tasks end to end, with its source available on GitHub under Apache-2.0. On Opper, launch it on GPT, Claude, Gemini, DeepSeek and 700+ more — one key, automatic fallbacks, and a choice of region.
CodexoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
NVIDIA-Nemotron-3-Ultra-550B-A55B runs on the routes below. Route only to EU providers when your data has to stay in Europe. One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | ||
|---|---|---|---|---|---|---|---|---|
| US | No | $0.50 | $2.20 | $0.10 | ||||
| US | No | $0.90 | $1.70 | Input price | Not offered on this route | Not offered on this route | ||
| Multi | No | $1.00 | $3.00 | Input price | Not offered on this route | Not offered on this route |
NVIDIA Nemotron 3 Ultra 550B A55B is a 550B Mixture-of-Experts model with 55B active parameters for complex multi-agent reasoning.
Step-by-step setup for running Codex on each of these models through Opper.
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claude
DeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.
OpenAI-compatible
GitHub's terminal coding agent. Point its provider variables at Opper to run it on any model, no Copilot plan required.
OpenAI-compatible