A dynamic routing API that identifies the optimal AI model for specific tasks based on performance, cost, and complexity.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smart-spawn
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 smart-spawn 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 Smart Spawn API?
The Smart Spawn API is a high-performance utility designed to remove the guesswork from LLM selection. By providing a simple HTTP interface, it allows developers to query for the most suitable model based on live benchmark data and specific task categories such as coding, reasoning, or vision. This tool ensures that your Openclaw Skills always operate with the best possible balance of intelligence and cost efficiency.
Integration is seamless and requires no local plugins, making it an ideal middleware for any agentic workflow. Whether you are building complex software or simple automations, the API provides the intelligence layer needed to route prompts to the provider that offers the highest success rate for your specific budget.
Smart Spawn API Use Cases
- Selecting the most cost-effective model for high-volume, low-complexity tasks within Openclaw Skills.
- Identifying top-tier reasoning models for complex debugging or architecture design sessions.
- Automatically falling back to alternative providers when a primary model experiences rate limits or downtime.
- Routing vision-specific tasks to models with the highest multi-modal benchmarks.
How Smart Spawn API Works
- The user or agent sends a GET or POST request to the API with a task description and optional budget constraints.
- The system analyzes the task against a database of model capabilities and real-time benchmark scores refreshed every 6 hours.
- The API returns a JSON response containing a specific model ID, pricing data, and a scoring rationale.
- The developer injects the returned model ID into the spawn command of their Openclaw Skills to initialize the sub-agent.
Smart Spawn API Setup
No installation or plugin is required to use this skill. You can interact with the API directly using any standard HTTP client.
# Example: Pick the best model for a coding task
curl "https://ss.deeflect.com/api/pick?task=coding&budget=medium"
Smart Spawn API Data Schema & Taxonomy
The API returns structured JSON data to ensure compatibility with various Openclaw Skills. Below is the primary schema for model selection:
| Attribute | Description |
|---|---|
| id | The unique identifier for the model (e.g., anthropic/claude-3.5-sonnet). |
| name | The human-readable display name of the AI model. |
| score | An internal performance metric (0-100) for the specific task category. |
| pricing | An object containing prompt and completion costs per million tokens. |
| reason | A detailed explanation of why this model was selected for the task. |
Smart Spawn API Advanced Features
- Task Decomposition: Automatically break complex prompts into a series of sub-tasks, each with its own recommended model.
- Swarm DAG Generation: Create a dependency graph for parallel agent execution across different specialized models.
- Multi-Model Comparison: Compare side-by-side metrics for specific model IDs to make manual overrides easier within Openclaw Skills.
- Real-time Health Checks: Monitor the status of upstream providers and data sources to ensure routing reliability.
SKILL.md
Loading
Related Openclaw Skills
Clawracle Oracle Resolver
An AI agent skill that enables participation in the Clawracle decentralized oracle network on Monad to earn tokens for data resolution.
strawpoll-cli
A comprehensive command-line interface for the StrawPoll API v3 that enables the creation and management of multiple-choice, meeting, and ranking polls.
LaMetric CLI
A comprehensive command-line tool for sending notifications and managing LaMetric TIME/SKY smart displays.
irail-cli
A command-line interface for querying Belgian railway data, including live departures, connections, and service disruptions via the iRail API.
Aegis Shield
Aegis Shield is a security screening tool designed to prevent prompt injection and data exfiltration by sanitizing untrusted text before it interacts with your AI agent memory or logic.
Signet API
A specialized trust scoring platform that provides autonomous AI agents with a verifiable identity and reputation score to enable secure transactions.
Featured*
