chat-gpt-6-luna
GitHub调用 GPT-6-Luna 模型处理高并发、成本敏感的编码、聊天、推理、RAG、摘要及翻译任务，支持长上下文与结构化输出。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill chat-gpt-6-luna -g -y
SKILL.md
Frontmatter
{
"name": "chat-gpt-6-luna",
"description": "Chat with gpt-6-luna, the most efficient model of OpenAI's GPT-6 family, built for high-volume, cost-sensitive work, with a 272K-token context window, adjustable reasoning effort, function calling, and structured outputs. Use for high-volume, cost-sensitive coding, chat, reasoning, RAG, summarization, and translation work. Half the price of chat-gpt-5-6-luna on input over the same context.",
"allowed-tools": "Bash(zerogpu chat_completions *)",
"argument-hint": "<text>"
}
Call gpt-6-luna. $ARGUMENTS is the raw prompt — pass it verbatim, no escaping or quoting required (the heredoc below handles every shell metacharacter, newline, quote, and paren safely):
zerogpu chat_completions -m gpt-6-luna <<'ZGPU_END_OF_INPUT'
$ARGUMENTS
ZGPU_END_OF_INPUT
At $0.10 / $0.50 per 1M input/output tokens this costs half /zerogpu-router:chat-gpt-5-6-luna on input and under half on output, over the same 272K-token window, and two thirds of /zerogpu-router:chat on input for a window twice as large. Prefer it over chat-gpt-5-6-luna unless the task specifically wants GPT-5.6's behaviour.
Output is the assistant's answer as plain text. Relay the answer as-is — do not rewrite or expand it.
Savings note: only if the command output literally contains a line starting with 💰 ZeroGPU savings, append that exact line, unchanged, as the last line of your reply. If no such line is present, say nothing about savings and do not mention or suggest /zerogpu-router:cost-savings — this note is intentionally occasional, not shown every time.
Version History
- 605eceb Current 2026-11-02 19:12
