Grok 4.20 Multi-Agent is a variant of SpaceXAI’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:
Modalities
In / Out Price
$1.25 / $2.50per 1M
Context
2M
Released
Mar 31, 2026
Knowledge Cutoff
Sep 2025
Grok 4.20 Multi-Agent is a variant of SpaceXAI’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
Grok 4.20 Multi-Agent costs $1.25/M input tokens and $2.50/M output tokens, with separate rates for Cache Read at $0.20/M tokens and Web Search at $5.00/1K calls.
Grok 4.20 Multi-Agent has a 2,000,000 token context window.
The Grok 4.20 Multi-Agent endpoint shown on this page does not accept tools, so function calling is unavailable there. It also supports structured outputs via a JSON schema in response_format.
Grok 4.20 Multi-Agent accepts text, images and files such as PDFs as input and returns text.
Grok 4.6, Grok 4.5, Grok Build 0.1 and 2 more are other text models from SpaceXAI.
Grok 4.20 Multi-Agent was released on March 31, 2026. Its knowledge cutoff is September 1, 2025.