Gemini API CLI 发布：给现有 agent 调 API 的命令行工具
Google 推出无状态 Gemini API CLI，可让 Claude Code、Codex、Cursor 等 agent 直接生成图像/视频/语音、分析 PDF 与 YouTube 链接、转录音频并跑 Deep Research。
We launched the Gemini API CLI. A CLI for calling the Gemini API. Give it to the agent you already use (Claude Code, Codex, Antigravity, Cursor, OpenClaw, Hermes...). It's NOT a new coding agent you can use it too: 1. Generate images, video, speech, music. 2. Analyze PDFs, images, audio, video, YouTube URLs, 3. Transcribe recordings to md / json / srt, 4. Run Deep Research in the background. Stateless. No memory, no chat mode. Your agent owns the context and the plan, gemini-api does the API call. Build for Agents, it's self-describing. `--help`, `--dry-run`... Start here: https://aistudio.google.com/learn/introducing-the-gemini-api-cli?e=0