Grok 4.20 Subagent
xAI's subagent variant of Grok 4.20 for collaborative deep research. Multiple agents operate in parallel to coordinate tool use and synthesize information across complex tasks. Scales from 4 to 16 agents based on reasoning effort. 2M-token context with image support.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Providers
Compare with
Frequently Asked Questions about Grok 4.20 Subagent▼
Who created Grok 4.20 Subagent?
▼
Grok 4.20 Subagent was created by xAI.
Is Grok 4.20 Subagent a reasoning model?
▼
No, Grok 4.20 Subagent is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Grok 4.20 Subagent support image or vision input?
▼
No, Grok 4.20 Subagent does not currently support image or vision input. It is a text-only model.
Does Grok 4.20 Subagent support audio?
▼
No, Grok 4.20 Subagent does not support audio input.
Is Grok 4.20 Subagent open source?
▼
Grok 4.20 Subagent is a proprietary model developed by xAI. The model weights and training data are not publicly available.
Where can I use Grok 4.20 Subagent?
▼
You can chat with Grok 4.20 Subagent on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Grok 4.20 Subagent through xAI's own API or platform.