Grok 4.20 Multi-Agent is xAI's model purpose-built for multi-agent orchestration and collaboration, part of the Grok 4.20 beta generation.
import { streamText } from 'ai'
const result = streamText({ model: 'xai/grok-4.20-multi-agent', prompt: 'Why is the sky blue?'})Grok 4.20 Multi-Agent was released March 9, 2026 as part of xAI's Grok 4.20 beta generation, purpose-built for multi-agent orchestration and collaboration. While the other Grok 4.20 variants focus on individual reasoning or speed, Grok 4.20 Multi-Agent targets workflows where multiple agents work together, coordinating tool calls, sharing context, and delegating subtasks.
The model features the same low hallucination rates and strict prompt adherence as its Grok 4.20 siblings, applied specifically to multi-agent challenges: consistent behavior across agent interactions, reliable handoffs, and predictable tool-calling patterns.
This model is currently in beta.