stepfun-openrouter
Integrates StepFun AI models (Step-3.5 Flash, Step-3) via OpenRouter API. Free tier available. Features visible reasoning, fast responses, and multimodal capabilities.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/mig6671/stepfun-openrouterStepFun via OpenRouter 🚀🧠
Fast, visible reasoning AI from StepFun — accessible via OpenRouter
A complete OpenClaw skill that integrates StepFun's powerful reasoning models through OpenRouter's unified API.
🆓 FREE TIER AVAILABLE
Start using Step-3.5 Flash immediately, no credit card required!
Quick Start
1. Get API Key
Visit https://openrouter.ai/keys and create a free API key.
2. Configure
export OPENROUTER_API_KEY="your-key-here"
3. Use
stepfun-cli "Hello!"
stepfun-cli --reasoning "Explain quantum computing"
Available Models
| Model | Price | Description |
|---|---|---|
| stepfun/step-3.5-flash:free | FREE | Fast, efficient reasoning |
| stepfun/step-3.5-flash | ~$0.20/M tokens | Production-grade |
| stepfun-ai/step3 | Variable | Advanced multimodal |
Features
- 🧠 Visible reasoning - see how AI thinks
- ⚡ Streaming responses
- 🖼️ Multimodal support
- 🔧 Full CLI with all options
Installation
clawhub install stepfun-openrouter
Links
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-mig6671-stepfun-openrouter": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
polymarket-news-monitor
Monitor official Polymarket sources (The Oracle blog, API status) for important updates, security alerts, and breaking news. Automatic importance scoring with instant notifications for critical events.
stepfun-openrouter
Integrates StepFun AI models (Step-3.5 Flash, Step-3) via OpenRouter API. Free tier available. Features visible reasoning, fast responses, and multimodal capabilities.
vector-memory-hack
Fast semantic search for AI agent memory files using TF-IDF and SQLite. Enables instant context retrieval from MEMORY.md or any markdown documentation. Use when the agent needs to (1) Find relevant context before starting a task, (2) Search through large memory files efficiently, (3) Retrieve specific rules or decisions without reading entire files, (4) Enable semantic similarity search instead of keyword matching. Lightweight alternative to heavy embedding models - zero external dependencies, <10ms search time.
minimal-test-skill
Minimal test skill for debugging ClawHub publishing
phoenix-shield
Self-healing backup and update system with intelligent rollback. Protects against failed updates by automatically monitoring system health post-update and recovering from backups when needed. Features canary deployment testing, health baselines, smart rollback, and 24/7 automated monitoring. Use when performing critical system updates, managing production deployments, or ensuring high availability of services. Prevents downtime through pre-flight checks, integrity verification, and automatic recovery workflows.