Grok 4.20 Multi Agent Beta
Grok 4.20 Multi Agent Beta is the beta-tagged xAI multi-agent orchestration model in the Grok 4.20 generation. Use it when you want the same multi-agent focus as grok-4.20-multi-agent under a beta lifecycle identifier.
import { streamText } from 'ai'
const result = streamText({ model: 'xai/grok-4.20-multi-agent-beta', prompt: 'Why is the sky blue?'})Playground
Try out Grok 4.20 Multi Agent Beta by xAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Grok 4.20 Multi Agent Beta
Ask Grok 4.20 Multi Agent Beta anything to try it out.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
xAI | 2M | 1.6s | 710tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | +4 | 03/11/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by xAI
| Model |
|---|
| 256K | 0.4s | 134tps | $1.00/M | $2.00/M | Read: $0.2/M Write: — | $5/K + input costs | — | +3 | | 05/20/2026 | |||
| 1M | 1.0s | 141tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | +4 |  | 04/30/2026 | |||
| 2M | 0.4s | 148tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | +3 | | 03/10/2026 | |||
| 2M | 0.4s | 169tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | +4 | | 03/10/2026 | |||
| 1M | 0.3s | 94tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | — | +2 | | 11/19/2025 | |||
| 1M | 0.9s | 52tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | — | +3 | | 11/19/2025 |
About Grok 4.20 Multi Agent Beta
Grok 4.20 Multi Agent Beta was released March 11, 2026 as the beta-tagged variant of xAI's Grok 4.20 multi-agent model. The beta designation means xAI may still update the model's weights, orchestration behavior, or agent coordination patterns before declaring a stable release.
Grok 4.20 Multi Agent Beta shares the same multi-agent orchestration architecture as its stable counterpart: coordination between multiple agents, task delegation, and collaborative workflows. Multi-agent orchestration is still an emerging pattern, and the beta lifecycle gives xAI room to refine how agents discover capabilities, negotiate task boundaries, and handle failures.
Both the beta and stable multi-agent variants are available through Vercel AI Gateway under separate identifiers. Teams building multi-agent systems can experiment with Grok 4.20 Multi Agent Beta while keeping the non-beta grok-4.20-multi-agent as the production fallback.
What To Consider When Choosing a Provider
- Configuration: Grok 4.20 Multi Agent Beta is in beta. Expect potential changes before general availability.
- Configuration: This model is optimized for agent collaboration patterns. For single-agent workflows, the non-reasoning or reasoning Grok 4.20 variants may be more appropriate.
- Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Grok 4.20 Multi Agent Beta
Best For
- Multi-agent orchestration: Workflows where several agents coordinate tool calls, share context, and hand off subtasks reliably
- Agent delegation workflows: A supervisor agent routes subtasks to specialist agents
- Complex automation pipelines: Requiring multiple agents with different roles to collaborate
- Tool-calling coordination: Agents need to share context and hand off results reliably
- Research and analysis systems: That decompose large problems across specialized agent roles
Consider Alternatives When
- Single-agent workflows: Grok 4.20 Non-Reasoning or Reasoning variants are better suited
- Speed-focused single-agent tasks: Grok 4.1 Fast Non-Reasoning provides fast tool calling without multi-agent overhead
- Stable production deployments: Beta models introduce risk. Wait for general availability or use Grok 4.1 Fast models
- Simple text generation: General-purpose Grok models handle the task without multi-agent optimization
Conclusion
Grok 4.20 Multi Agent Beta offers early access to Grok 4.20 multi-agent orchestration while xAI refines coordination patterns. For production multi-agent pipelines, prefer the non-beta grok-4.20-multi-agent for stable behavior.