AI/ML API LLM + Reasoning for OpenClaw

封装 run_chat.py 脚本调用 AIMLAPI 聊天补全接口，从 AIMLAPI_API_KEY 读取密钥，携带 User-Agent 发送请求并支持重试；通过参数传入模型、system/user 提示与 extra-json（如 reasoning、response_format）获取文本或 JSON 结果，也可写入输出文件。

aimlapihello

热度 89.95

最近更新 2026-05-17 11:50:58

分类：开发依赖：代码执行 / 第三方 API / 内部调用大模型 / 读写文件应用场景：API 集成 / 自动化脚本 / 摘要总结 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add aiml-llm-reasoning

Metadata

name: aimlapi-llm-reasoning
description: Run AIMLAPI LLM and reasoning workflows through chat completions with retries, structured outputs, and explicit User-Agent headers. Use when Codex needs scripted prompting/reasoning calls against AIMLAPI models.
env: ["AIMLAPI_API_KEY"]
primaryEnv: AIMLAPI_API_KEY

AIMLAPI LLM + Reasoning

Overview

Use run_chat.py to call AIMLAPI chat completions with retries, optional API key file fallback, and a User-Agent header on every request.

Quick start

export AIMLAPI_API_KEY="sk-aimlapi-..."
python3 {baseDir}/scripts/run_chat.py --model aimlapi/openai/gpt-5-nano-2025-08-07 --user "Summarize this in 3 bullets."

Tasks

Run a basic chat completion

python3 {baseDir}/scripts/run_chat.py \
  --model aimlapi/openai/gpt-5-nano-2025-08-07 \
  --system "You are a concise assistant." \
  --user "Draft a project kickoff checklist." \
  --user-agent "openclaw-custom/1.0"

Add reasoning parameters

python3 {baseDir}/scripts/run_chat.py \
  --model aimlapi/openai/gpt-5-nano-2025-08-07 \
  --user "Plan a 5-step rollout for a new chatbot feature." \
  --extra-json '{"reasoning": {"effort": "medium"}, "temperature": 0.3}'

Structured JSON output

python3 {baseDir}/scripts/run_chat.py \
  --model aimlapi/openai/gpt-5-nano-2025-08-07 \
  --user "Return a JSON array of 3 project risks with mitigation." \
  --extra-json '{"response_format": {"type": "json_object"}}' \
  --output ./out/risks.json

References

references/aimlapi-llm.md: payload and troubleshooting notes.
README.md: changelog-style summary of new instructions.