A zero-plugin HTTP API that dynamically selects the most cost-effective and high-performing AI models for any specific task or sub-agent spawn.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smart-spawn-api
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-api 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 powerful routing engine designed to eliminate the guesswork in model selection for autonomous agents. By integrating this into your Openclaw Skills, you can programmatically determine which LLM offers the best balance of performance and price for tasks ranging from simple coding to complex multi-step reasoning.
Built for developers who need high-velocity deployment, it requires no heavy plugins or local configuration. It functions as a lightweight intelligence layer that sits between your task definition and the execution phase, ensuring that every session_spawn call uses an optimized model backed by real-time benchmark data.
Smart Spawn API Use Cases
- Automatically selecting a low-cost model for simple unit tests to save on API credits.
- Routing high-complexity architectural tasks to top-tier reasoning models like Claude Opus.
- Orchestrating multi-agent swarms where each sub-task is assigned to a specialized model (e.g., vision, coding, or research).
- Building fallback logic into Openclaw Skills to maintain uptime when specific model providers experience latency.
How Smart Spawn API Works
- The user or agent sends an HTTP GET request to the pick endpoint with a description of the task and a preferred budget tier.
- The Smart Spawn API analyzes the task category against its database of benchmarked performance scores.
- The API returns a JSON response containing the optimal model ID, its pricing profile, and the reasoning behind the choice.
- The agent passes the returned model ID directly into the sessions_spawn function.
- For complex projects, the agent utilizes the decompose or swarm endpoints to create a multi-model execution graph.
Smart Spawn API Setup
Since this is a cloud-based API, no local installation is required. You can test the integration directly from your terminal using curl:
# Quick test to find a coding model
curl "https://ss.deeflect.com/api/pick?task=coding&budget=medium"
To integrate with your Openclaw Skills, simply use your preferred HTTP library to fetch the model ID before spawning a new session.
Smart Spawn API Data Schema & Taxonomy
The API provides structured JSON responses updated every 6 hours. Key data points include:
| Field | Type | Description |
|---|---|---|
id |
String | The provider-specific model identifier used for spawning. |
score |
Integer | A performance rating (0-100) based on 5 benchmark sources. |
pricing |
Object | Includes prompt and completion costs per million tokens. |
reason |
String | Human-readable explanation of why this model was selected. |
Smart Spawn API Advanced Features
- Task Decomposition: Automatically break down a high-level prompt into a sequence of sub-tasks with specialized models.
- Parallel Swarm Graphs: Generate a dependency graph (DAG) for multi-agent systems to execute tasks in parallel.
- Budget Guardrails: Filter models based on specific tiers (low, medium, high) to prevent unexpected API costs.
- Real-time Comparison: Side-by-side capability and pricing analysis between two or more specific model IDs.
SKILL.md
Loading
Related Openclaw Skills
Crypto & Stock Market Data (Node.js)
A professional-grade financial data integration for AI agents providing real-time crypto and stock market metrics without the need for external dependencies.
Model Router
Model Router is a self-aware routing engine for OpenClaw that dynamically matches specific tasks to the most capable and cost-effective AI models available in your configuration.
kk-daily-backup-report
A mobile-optimized reporting skill that provides concise, categorized daily backup status updates for servers and personal data.
GitHub AI Trends
A specialized tool for generating formatted leaderboards of trending GitHub AI projects based on real-time star counts and activity.
Ops Detection & Incident Routing
A production-grade toolkit for detecting agent runtime anomalies and routing incidents through deterministic, approval-safe guardrails.
Supabase REST Checkpointer
A durable LangGraph checkpointing solution that persists agent state via the Supabase PostgREST API without requiring a direct Postgres connection.
Featured*
