Grok 4.20 Multi-Agent Beta reasoning
Grok 4.20 Multi-Agent Beta is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.
Reasoning effort behavior:
- low / medium: 4 agents
- high / xhigh: 16 agents
Capabilities
Context Window 2M tokens
Max Output 0 tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $2.00
Output $6.00
Cache Read $0.20
Cache Write -
Supported Parameters
include_reasoninglogprobsmax_tokensreasoningresponse_formatseedstructured_outputstemperaturetop_logprobstop_p