# Wavespeed

> 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.

- **Type:** Skill
- **Install:** `agentstack add skill-wesleysimplicio-wavespeedai-skills-openclaw`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [wesleysimplicio](https://agentstack.voostack.com/s/wesleysimplicio)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [wesleysimplicio](https://github.com/wesleysimplicio)
- **Source:** https://github.com/wesleysimplicio/WaveSpeedAI-Skills/tree/main/agents/openclaw
- **Website:** https://wavespeed.ai

## Install

```sh
agentstack add skill-wesleysimplicio-wavespeedai-skills-openclaw
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# WaveSpeedAI (OpenClaw)

Unified inference gateway. Async-by-default with automatic polling. Same surface for image/video/audio and LLM.

## When to use

- User asks for AI media generation (image, video, audio, avatar).
- User mentions a `wavespeed-ai/*` model uuid.
- User wants to upload a local image/video as input for image-to-X.
- User wants to call Claude / GPT / Gemini / Llama through the WaveSpeed LLM proxy.
- User wants the WaveSpeed model catalog or account balance.

## Setup

```bash
export WAVESPEED_API_KEY="ws_..."
# Install once if missing:
bash  --wait
wavespeed-cli cancel 

# Models & balance
wavespeed-cli models --names-only
wavespeed-cli balance

# LLM
wavespeed-cli llm anthropic/claude-opus-4.6 "Hello" --system "Be terse."
wavespeed-cli llm openai/gpt-5.2-pro "..." --stream
```

## Common model uuids

| Use | uuid |
|---|---|
| Fast text→image | `wavespeed-ai/z-image/turbo` |
| Quality text→image | `wavespeed-ai/flux-dev`, `wavespeed-ai/flux-pro` |
| Image→video | `wavespeed-ai/seedance-v2`, `wavespeed-ai/kling-v2.1` |
| Text→video w/ audio | `wavespeed-ai/veo-3` |
| Audio | `wavespeed-ai/ace-step` |
| LLM | `anthropic/claude-opus-4.6`, `openai/gpt-5.2-pro`, `google/gemini-3-flash-preview` |

## Errors

`401` bad key · `400` payload schema · `402` insufficient balance · `404` not found · `429` rate-limited · `5xx` upstream.

## Refs

- Docs: https://wavespeed.ai/docs
- API key: https://wavespeed.ai/accesskey
- Models: https://wavespeed.ai/models
- Skill repo: https://github.com/wesleysimplicio/WaveSpeedAI-Skills

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [wesleysimplicio](https://github.com/wesleysimplicio)
- **Source:** [wesleysimplicio/WaveSpeedAI-Skills](https://github.com/wesleysimplicio/WaveSpeedAI-Skills)
- **License:** MIT
- **Homepage:** https://wavespeed.ai

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-wesleysimplicio-wavespeedai-skills-openclaw
- Seller: https://agentstack.voostack.com/s/wesleysimplicio
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.