chat-deepseek
GitHub调用 ZeroGPU API 使用 deepseek-v4-flash 模型,适用于代码阅读、编写、重构及多步自动化规划。该模型上下文窗口大且成本低,适合处理大型代码库和复杂工具调用任务。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill chat-deepseek -g -y
SKILL.md
Frontmatter
{
"name": "chat-deepseek",
"metadata": {
"openclaw": {
"install": [
{
"bins": [
"zerogpu"
],
"kind": "node",
"package": "zerogpu-cli"
}
],
"requires": {
"bins": [
"zerogpu"
]
}
}
},
"description": "Chat with deepseek-v4-flash, a 284B MoE model (13B active per token) with a 1M-token context window, tuned for coding and agentic workflows. Use for reading or writing code across a large codebase, porting and refactoring, or planning multi-step automation. Cheaper than chat-glm at the same context size.",
"allowed-tools": "Bash(zerogpu chat *)",
"argument-hint": "<text> [-i <instructions>]"
}
Sends your input to ZeroGPU's hosted API for inference — this is not local processing. Don't pass secrets, credentials, or regulated data you aren't cleared to share with a third party. See the plugin README's "Data & privacy" section.
Call deepseek-v4-flash. $ARGUMENTS is the raw prompt — pass it verbatim, no escaping or quoting required (the heredoc below handles every shell metacharacter, newline, quote, and paren safely):
ZGPU_TEXT=$(cat <<'ZGPU_END_OF_INPUT'
$ARGUMENTS
ZGPU_END_OF_INPUT
)
zerogpu chat "$ZGPU_TEXT" -m deepseek-v4-flash
If the user supplied system instructions, append -i "<instructions>" after the model flag.
At $0.07 / $0.14 per 1M input/output tokens this is the cheaper of the two 1M-context models — roughly a sixteenth of chat-glm. Prefer it whenever the task is code or tool-use rather than sheer input size. For a prompt that fits in 131K tokens, chat is cheaper still.
This model is served by the Chat Completions API rather than the Responses API; the CLI routes it automatically. Output is the assistant's answer as plain text — the model's reasoning trace is omitted, since this skill does not pass the CLI's -r flag. 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 the cost-savings skill — this note is intentionally occasional, not shown every time.
Version History
- cee9321 Current 2026-08-02 21:15


