venice-router
Supreme model router for Venice.ai — the privacy-first, uncensored AI platform. Automatically classifies query complexity and routes to the cheapest adequate model. Supports web search, uncensored mode, private-only mode (zero data retention), conversation-aware routing, cost budgets, function calling, and 30+ Venice.ai text models. Use when the user wants to chat via Venice.ai, send prompts through Venice, or needs smart model selection to minimize API costs while keeping data private from Big Tech.
Why use this skill?
Optimize your OpenClaw workflow with the venice-router. Automate model selection, reduce costs, and ensure private, uncensored AI interactions.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/plusone/venice-ai-router-openclawWhat This Skill Does
The venice-router is a sophisticated orchestration layer for OpenClaw designed to interact with Venice.ai, a privacy-centric AI ecosystem. It acts as an intelligent intermediary that evaluates the complexity of a user prompt and automatically selects the most cost-effective and capable model from a catalog of over 30 options. Beyond simple routing, it enforces Venice's core value proposition: zero data retention, no content filtering, and complete avoidance of Big Tech surveillance. Whether you are performing high-stakes research or creative writing, the router manages the infrastructure so you don't have to navigate model tiers manually.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/plusone/venice-ai-router-openclaw
Once installed, you must configure your credentials to begin. Obtain your API key from venice.ai/settings/api. You can set this globally by exporting VENICE_API_KEY in your shell environment or by adding it to your ~/.openclaw/openclaw.json configuration file. Ensure the key has proper permissions for model access.
Use Cases
This skill is ideal for privacy-focused developers and writers who want to leverage uncensored, open-weight models without the overhead of manual model selection. Use cases include:
- Private Data Analysis: Routing confidential contracts to zero-retention private models.
- Cost Optimization: Automatically downgrading trivial queries to low-cost models while preserving capacity for complex tasks like code generation.
- Uncensored Creative Writing: Bypassing the restrictive guardrails of Big Tech models.
- Web Research: Utilizing live search capabilities with source citation.
- Complex Workflow Orchestration: Handling multi-turn conversations and function calling with persistent context awareness.
Example Prompts
- "Route a request to write a python script for scraping financial data using the uncensored mode to ensure no filtering."
- "Search the web for the latest advancements in local LLM security and provide a summary using the mid-tier model for optimal balance."
- "Analyze the attached history file and suggest a follow-up response regarding the distributed system architecture, keeping budget constraints in mind."
Tips & Limitations
- The router defaults to 'auto', but you can force specific tiers (--tier cheap|mid|premium) to maintain performance consistency.
- Function calling automatically requires at least a 'mid' tier model; the router handles this internal requirement gracefully.
- Monitor your expenses using the --budget-status flag to prevent over-utilization.
- Always remember that while the models are uncensored, your input is sent to the Venice.ai API endpoints; ensure your network connection is secure.
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-plusone-venice-ai-router-openclaw": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api