Skill v1.0.3

name: chat description: Chat reply via ZeroGPU's default model, gpt-oss-120b (120B MoE, 131K context). Use when the user wants an answer from a ZeroGPU model rather than Claude, including longer documents, multi-step instructions, and harder general-knowledge questions. argument-hint: "<text>" allowed-tools: Bash(zerogpu chat_completions *) metadata: version: "1.0.3"

Call the ZeroGPU chat model. $ARGUMENTS is the raw prompt. Pass it verbatim, with no escaping or quoting required (the heredoc below handles every shell metacharacter, newline, quote, and paren safely):

zerogpu chat_completions -m gpt-oss-120b <<'ZGPU_END_OF_INPUT'
$ARGUMENTS
ZGPU_END_OF_INPUT

Output is the assistant's answer as plain text. The model also produces a reasoning trace, which the Chat Completions response carries separately, so only the final answer is printed. Relay that answer as-is, without rewriting or expanding it.

For a faster, cheaper reply where quality matters less, use /zerogpu-router:chat-liquid (LFM2.5-1.2B-Instruct). For a visible reasoning trace, use /zerogpu-router:chat-thinking. For multilingual prompts, use /zerogpu-router:chat-qwen. When the input does not fit in this model's 131K context, use /zerogpu-router:chat-glm-5-3-flash or /zerogpu-router:chat-deepseek-v4-1-flash for code and agentic work, or /zerogpu-router:chat-gpt-4-1-mini when instruction following and tool calling matter most — glm-5.3-flash, deepseek-v4.1-flash, and gpt-4.1-mini each carry a 1M-token context, and gpt-4.1-mini costs roughly 2.7x this skill on input and output alike.

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.