菜单
WaveSpeedAI inference gateway — 700+ media models and 290+ OpenAI-compatible LLMs through one API key. Use for AI media generation (image/video/audio/avatar) and for cheap proxied LLM calls (Claude/GPT/Gemini/Llama).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate images, video, audio and avatars via the WaveSpeedAI inference platform (700+ models incl. FLUX, Kling, Veo, Luma, Stable Diffusion, Seedance, Z-Image, Wan, Qwen, Higgsfield), or call the OpenAI-compatible LLM gateway (290+ models incl. Claude, GPT, Gemini, DeepSeek, Llama, Mistral). Use whenever the user asks to create AI media, run a `wavespeed-ai/*` model, upload a media asset for inference, list available models, check account balance, configure a webhook, or call an LLM through the WaveSpeed proxy. Wraps the official Python SDK (`pip install wavespeed`) plus a thin CLI for one-shot calls.
Generate images, video, audio, avatars (700+ models — FLUX, Kling, Veo, Luma, Seedance, Z-Image, Wan) or call OpenAI-compatible LLMs (290+ — Claude, GPT, Gemini, DeepSeek, Llama) via the WaveSpeedAI inference platform. Wraps the official Python SDK plus a thin CLI shim.
Generate images, video, audio and avatars (700+ models) or call OpenAI-compatible LLMs (290+ models — Claude, GPT, Gemini, DeepSeek, Llama) through the WaveSpeedAI inference platform. Use whenever the user asks to create AI media, run a `wavespeed-ai/*` model, upload a media asset for inference, list available models, check account balance, or call an LLM via the WaveSpeed proxy.
WaveSpeedAI inference gateway — 700+ media models (FLUX, Kling, Veo, Luma, Seedance, Z-Image, Wan, Qwen, Higgsfield) and 290+ OpenAI-compatible LLMs (Claude, GPT, Gemini, Llama, DeepSeek, Mistral) through one API key. Wraps the official Python SDK and a thin CLI.
WaveSpeedAI inference gateway — 700+ media models (FLUX, Kling, Veo, Luma, Seedance, Z-Image, Wan, Qwen, Higgsfield, ace-step) and 290+ OpenAI-compatible LLMs through one API key. Use whenever the user wants to generate AI media, list available models, check balance, or call Claude/GPT/Gemini through the WaveSpeed LLM proxy.
WaveSpeedAI inference gateway — 700+ media models and 290+ OpenAI-compatible LLMs in one API. Use for AI image/video/audio generation and for cheap proxied LLM calls.
| name | wavespeed |
| description | WaveSpeedAI inference gateway — 700+ media models and 290+ OpenAI-compatible LLMs through one API key. Use for AI media generation (image/video/audio/avatar) and for cheap proxied LLM calls (Claude/GPT/Gemini/Llama). |
wavespeed-ai/* uuid.export WAVESPEED_API_KEY="ws_..." # https://wavespeed.ai/accesskey
CLI shim: ~/.local/bin/wavespeed-cli (run install.sh from the repo if missing).
wavespeed-cli run wavespeed-ai/z-image/turbo '{"prompt":"Cat"}'
URL=$(wavespeed-cli upload ./input.png)
wavespeed-cli run wavespeed-ai/seedance-v2 '{"image":"'"$URL"'","prompt":"camera dolly"}'
wavespeed-cli submit wavespeed-ai/veo-3 '{"prompt":"..."}' --webhook-url https://app/cb
wavespeed-cli result <id> --wait
wavespeed-cli models --names-only
wavespeed-cli balance
wavespeed-cli llm anthropic/claude-opus-4.6 "Summarize in one sentence."
Output URLs live at .outputs[] of the printed JSON.
import wavespeed
out = wavespeed.run("wavespeed-ai/z-image/turbo", {"prompt": "Cat"})
print(out["outputs"][0])