Codex CLI setup
Codex CLI, any model.
One command adds an Aethene provider to Codex. Your key stays in your keychain — Codex asks the CLI for it.
Steps
$ curl -fsSL https://3-229-227-242.sslip.io/install.sh | sh$ aethene login$ aethene install codex$ codexWhat happens
No key in the config file
Codex runs `aethene token` to fetch your key, so it never sits in config.toml.
Choose the model
aethene install codex --model aethene/gpt-6-astra makes Astra the Codex default; aethene/gpt-6-sol is the default otherwise.
Clean undo
aethene uninstall codex restores your original config.
As of 2026-09-25: a typical Claude Code turn costs $0.068 on aethene/claude-opus and $0.0020 on aethene/gpt-6-luna.
Models
Every model on the same key
Claude Opus 5.5
Anthropic's Opus flagship. Claude Code default.
- Input
- $5.00
- Output
- $25.00
- Context
- 1M
GPT-6 Astra
OpenAI's frontier model for the most demanding work.
- Input
- $12.50
- Output
- $62.50
- Context
- 1M
GPT-6 Sol
Fast, capable all-rounder. Chat default.
- Input
- $2.50
- Output
- $12.50
- Context
- 1.1M
GPT-6 Luna
The budget model for quick, high-volume work.
- Input
- $0.13
- Output
- $0.63
- Context
- 1.1M
GPT-4o
The reliable multimodal classic.
- Input
- $3.13
- Output
- $12.50
- Context
- 128K
DeepSeek V4 Pro
DeepSeek's flagship. Strong coding and reasoning at a low price.
- Input
- $2.18
- Output
- $4.35
- Context
- 1M
DeepSeek V4.1 Flash
Fast, very cheap DeepSeek model for everyday coding.
- Input
- $0.55
- Output
- $2.74
- Context
- 1M
Gemini 3.8 Flash
Google's fast thinking model, straight from Google.
- Input
- $0.94
- Output
- $4.69
- Context
- 1M
Auto
Tools or long context go to Claude Opus; short chat goes to the cheapest healthy GPT-6. Billed at the model it picks.
Questions