An integration skill that brings StepFun high-speed reasoning and multimodal AI models to your local environment via the OpenRouter API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install stepfun-openrouter
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install stepfun-openrouter using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is StepFun OpenRouter Integration?
This skill provides a seamless connection between the StepFun AI ecosystem and your local workspace using the OpenRouter API. By incorporating this into your Openclaw Skills library, you gain access to the Step-3.5 Flash and Step-3 models, which are renowned for their 'visible reasoning' capabilities—allowing you to see the logical steps the AI takes before reaching a conclusion.
Designed for speed and efficiency, the integration supports a free tier for developers looking to prototype quickly. It serves as a bridge for developers who need high-performance LLMs without the overhead of managing multiple proprietary API integrations, centralizing StepFun access through a unified interface.
StepFun OpenRouter Integration Use Cases
- Generating complex logic and code explanations using visible reasoning steps.
- Utilizing free tier AI models for automated testing and simple CLI tasks.
- Processing multimodal data including text and images through advanced Step-3 models.
- Rapidly prototyping AI-driven workflows within the broader ecosystem of Openclaw Skills.
How StepFun OpenRouter Integration Works
- The skill initializes by reading the OpenRouter API key from the local environment variables.
- When a command is issued via the CLI, the skill formats the request for the OpenRouter gateway.
- It specifies the desired StepFun model (e.g., Step-3.5 Flash) and enables streaming for real-time feedback.
- If the reasoning flag is active, the skill captures and displays the model's internal thinking process alongside the final response.
StepFun OpenRouter Integration Setup
To get started, first ensure you have an API key from the OpenRouter dashboard. Then, install the skill and set your credentials:
clawhub install stepfun-openrouter
export OPENROUTER_API_KEY="your-key-here"
You can verify the setup by running a simple query:
stepfun-cli "Verify installation"
StepFun OpenRouter Integration Data Schema & Taxonomy
The skill manages its configuration and model interactions through environment variables and standard CLI arguments. The following table outlines the primary data inputs:
| Parameter | Description | Required |
|---|---|---|
OPENROUTER_API_KEY |
Your unique authentication key from OpenRouter | Yes |
stepfun/step-3.5-flash:free |
The default free-tier model identifier | No |
--reasoning |
A flag to enable the display of AI thinking steps | No |
| Multimodal Input | Support for image paths or URLs for vision tasks | No |
StepFun OpenRouter Integration Advanced Features
- Visible reasoning support to debug and understand AI logic in real-time.
- Full multimodal capability for analyzing visual assets via Step-3 models.
- Streaming response support for low-latency interactions.
- Compatibility with OpenRouter's usage tracking and credit management.
- Lightweight CLI interface designed for easy integration into existing Openclaw Skills automation scripts.
SKILL.md
Loading
Related Openclaw Skills
StepFun via OpenRouter
A specialized integration that brings StepFun AI models with visible reasoning and multimodal capabilities to your terminal via OpenRouter.
Polymarket News Monitor
An automated tracking tool that monitors official Polymarket sources for security alerts, API health, and breaking news with intelligent importance scoring.
Minimal Test Skill
A lightweight diagnostic skill designed to verify and debug the publishing process for Openclaw Skills.
Universal Agent Messaging (UAM)
A secure communication protocol and toolset that allows AI agents to send and receive encrypted messages across different platforms.
Haskell Development
An expert-level skill for building, debugging, and optimizing production-grade Haskell applications with a focus on type safety and purity.
ZFS Administration
A comprehensive toolset for managing OpenZFS storage, from pool creation and dataset optimization to snapshots and troubleshooting.
METADATA
Featured*
