Model Router Premium for Openclaw

An intelligent request router that selects the most cost-effective LLM based on task complexity and model metadata.

mrjootta
v0.1.1
Feb 7, 2026
12
4.4k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install model-router-premium

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install model-router-premium 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 Model Router Premium?

Model Router Premium is a high-performance skill designed to optimize AI workflows by programmatically selecting the best LLM for any given task. By analyzing Openclaw Skills configurations, it balances operational costs with task complexity, ensuring that simple requests are handled by budget-friendly models while high-fidelity tasks are escalated to more powerful engines. This deterministic approach provides developers with a transparent and auditable way to manage multi-model environments efficiently.

Built on design principles of transparency and efficiency, this tool eliminates the guesswork of model selection. It uses explicit metadata like capabilities and cost scores to ensure that every request is routed to the most appropriate provider, making it an essential component for scaling AI-driven applications.

Model Router Premium Use Cases

  • Automating model selection for diverse user requests in production applications.
  • Implementing cost-control middleware for high-volume batch processing tasks.
  • Dynamic escalation of complex tasks from lightweight models to high-reasoning LLMs.
  • Auditing model performance and cost distribution through explicit metadata mapping.

How Model Router Premium Works

  1. The router parses a models configuration file containing metadata such as cost scores and capabilities.
  2. It analyzes the incoming task description using heuristics to determine complexity (e.g., input length, specific keywords).
  3. The logic checks for any explicit user overrides or caller hints that mandate a specific model.
  4. It evaluates the available models against the requirements to select the most efficient option.
  5. The skill returns the selected model identifier along with a detailed reasoning log for transparency.

Model Router Premium Setup

To integrate this into your workflow, ensure your environment is configured for Openclaw Skills and follow these steps:

# Navigate to your project directory
cd model-router-premium

# Prepare your models.json file with model metadata
# Run the router via the CLI to test a routing decision
python3 scripts/router.py --models examples/models.json --task "Summarize this email" --mode auto

Model Router Premium Data Schema & Taxonomy

The skill relies on a structured JSON configuration to define the available model landscape within Openclaw Skills.

Field Description Type
name The unique identifier for the LLM. String
provider The API provider (e.g., OpenAI, Anthropic). String
cost_score A relative integer representing the cost (lower is cheaper). Integer
capabilities List of supported features (e.g., vision, long-context). Array
tags Metadata for filtering (e.g., fast, premium). Array

Model Router Premium Advanced Features

  • Deterministic decision logic ensuring consistent routing outcomes across sessions.
  • Heuristic-based complexity analysis for automated model escalation without manual intervention.
  • Full transparency with explicit reasoning outputs for every routing decision made by the system.
  • Support for custom metadata tags to align with unique business logic in Openclaw Skills deployments.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*