xAI: Grok 4.20 Multi-Agent Beta
xAIID: x-ai/grok-4.20-multi-agent-beta
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
Pricing per 1M Tokens
| Input (Prompt) | $2.00 |
| Output (Completion) | $6.00 |
| Cache Read | $0.20 |
| Cache Write | Free |
| Image | N/A |
Specifications
| Context Length | 2M |
| Max Output Tokens | N/A |
| Input Modalities | Text + Image |
| Output Modalities | Text |
| Tokenizer | Grok |
| Instruct Type | N/A |
| Top Provider Context | 2M |
| Top Provider Max Output | N/A |
| Moderated | No |
Compare this model
See how xAI: Grok 4.20 Multi-Agent Beta stacks up against other models.
More from xAI
Last updated: March 23, 2026
First tracked: March 23, 2026