Aethene

8 models · rates as of 2026-09-25

Pick a model. Keep your key.

Every alias works in Claude Code, Codex, the API and the chat app. Switch any time with /model — your key, balance and history stay the same.

At a glance

Side by side

ModelBest forIn /1MOut /1MContextTypical turnEval
Claude Opus 5.5
aethene/claude-opus
Claude Code sessions, refactors, debugging across a codebase.$5.00$25.001M$0.068pending
GPT-6 Astra
aethene/gpt-6-astra
Hard planning, deep reviews and a strong second opinion.$12.50$62.501M$0.197pending
GPT-6 Sol
aethene/gpt-6-sol
Chat, Codex sessions, planning and everyday coding.$2.50$12.501.1M$0.039pending
GPT-6 Luna
aethene/gpt-6-luna
Quick questions, summaries, boilerplate and high-volume work.$0.13$0.631.1M$0.002pending
GPT-4o
aethene/gpt-4o
Existing prompts and apps already tuned for GPT-4o.$3.13$12.50128K$0.098pending
DeepSeek V4 Pro
aethene/deepseek-v4-pro
Everyday coding and long-context work when cost matters.$2.18$4.351M$0.023pending
DeepSeek V4.1 Flash
aethene/deepseek-v4-flash
Quick edits, summaries, boilerplate and high-volume work.$0.55$2.741M$0.009pending
Gemini 3.8 Flash
aethene/gemini-3-8-flash
Long documents, images, and fast reasoning at a low price.$0.94$4.691M$0.014pending

Our bar is at least 95% on a tool-call eval (multi-file edit, test-run-fix loop, long cached prompt, streaming cancel, sub-agent spawn), re-run weekly. Models are in beta until their scores are measured and published here.

Auto

aethene/auto picks for you

Requests with tools or long context go to Claude Opus; short chat goes to whichever of GPT-6 Sol and Luna is healthy and cheaper. You're billed at the model it picked, and your request log shows which one that was.

Set up in three minutes.

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