Claude Code setup in 3 minutes — no config editing

Steps

Step 1

$ curl -fsSL https://3-229-227-242.sslip.io/install.sh | sh

Installs one static binary (macOS, Linux; Windows via PowerShell).

Step 2

$ aethene login

Opens your browser to confirm; this machine gets its own key you can cap or revoke.

Step 3

$ aethene install claude

Backs up ~/.claude/settings.json, writes the gateway settings and adds 10 skills.

Step 4

$ claude

That's it. Pick any model with /model.

What happens

It sets exactly what Claude Code needs

Base URL (no /v1 suffix), your key, an empty ANTHROPIC_API_KEY so a stray Console key can't interfere, default models for Opus/Sonnet/Haiku slots and sub-agents, and every Aethene model in the /model picker.

Something off? Run doctor

aethene doctor finds stray API keys, /v1 suffixes, shell exports that override settings, project-level overrides and a cached claude.ai login — and prints the fix for each.

Undo is exact

aethene uninstall claude restores your original settings byte-for-byte and removes only Aethene's skills. Try it for one session instead with aethene claude.

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

aethene/claude-opus≈ $0.068 / turn

GPT-6 Astra

OpenAI's frontier model for the most demanding work.

Input: $12.50
Output: $62.50
Context: 1M

aethene/gpt-6-astra≈ $0.197 / turn

GPT-6 Sol

Fast, capable all-rounder. Chat default.

Input: $2.50
Output: $12.50
Context: 1.1M

aethene/gpt-6-sol≈ $0.039 / turn

GPT-6 Luna

The budget model for quick, high-volume work.

Input: $0.13
Output: $0.63
Context: 1.1M

aethene/gpt-6-luna≈ $0.002 / turn

GPT-4o

The reliable multimodal classic.

Input: $3.13
Output: $12.50
Context: 128K

aethene/gpt-4o≈ $0.098 / turn

DeepSeek V4 Pro

DeepSeek's flagship. Strong coding and reasoning at a low price.

Input: $2.18
Output: $4.35
Context: 1M

aethene/deepseek-v4-pro≈ $0.023 / turn

DeepSeek V4.1 Flash

Fast, very cheap DeepSeek model for everyday coding.

Input: $0.55
Output: $2.74
Context: 1M

aethene/deepseek-v4-flash≈ $0.009 / turn

Gemini 3.8 Flash

Google's fast thinking model, straight from Google.

Input: $0.94
Output: $4.69
Context: 1M

aethene/gemini-3-8-flash≈ $0.014 / turn

Auto

Tools or long context go to Claude Opus; short chat goes to the cheapest healthy GPT-6. Billed at the model it picks.

aethene/autoCompare all →

Questions

FAQs

Do I need an Anthropic account?

No. Aethene is the account: one key and one balance for every model.

Will it break my existing Claude Code setup?

Your settings are backed up first, and only Aethene's keys are added. If you change settings later and uninstall, Aethene removes only its own entries.

Claude Code still shows my old login

Run /logout inside claude once. While the Aethene key is set, it's used instead of your subscription login.

Set up in three minutes.