Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is SpaceXAI's model purpose-built for multi-agent orchestration and collaboration, part of the Grok 4.20 beta generation.
View API reference- Input and output price
- Input $1.25, Output $2.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'spacexai/grok-4.20-multi-agent', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Grok 4.20 Multi-Agent by SpaceXAI. 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
Grok 4.20 Multi-Agent
Copy link to headingProviders
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.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Grok 4.20 Multi-Agent through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Grok 4.20 Multi-Agent request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. spacexai/grok-4.20-multi-agent. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Grok 4.20 Multi-Agent supports up to 2,000,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 2M-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK xai provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['xai'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.20-multi-agent', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by SpaceXAI
| Model |
|---|
| 500K | $2/M+1 more | $6/M+1 more | Read$0.50/M | $5/K | +1 | | 08/12/2026 | |||||||
| 500K | $2/M+1 more | $6/M+1 more | Read$0.30/M | $5/K | +3 | | 07/08/2026 | |||||||
| 1M | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +3 |  | 04/30/2026 | |||||||
| 2M | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +2 | | 03/10/2026 | |||||||
| 1M | $0.20/M | $0.50/M | Read$0.05/M | — | +1 | | 11/19/2025 | |||||||
| 1M | $0.20/M | $0.50/M | Read$0.05/M | — | +2 | | 11/19/2025 |
Copy link to headingAbout Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent was released March 10, 2026 as part of SpaceXAI's Grok 4.20 beta generation, purpose-built for multi-agent orchestration and collaboration. While the other Grok 4.20 variants focus on individual reasoning or speed, Grok 4.20 Multi-Agent targets workflows where multiple agents work together, coordinating tool calls, sharing context, and delegating subtasks.
The model features the same low hallucination rates and strict prompt adherence as its Grok 4.20 siblings, applied specifically to multi-agent challenges: consistent behavior across agent interactions, reliable handoffs, and predictable tool-calling patterns.
This model is currently in beta.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Grok 4.20 Multi-Agent 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: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Grok 4.20 Multi-Agent
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
Copy link to headingConclusion
Grok 4.20 Multi-Agent opens up multi-agent orchestration as a first-class use case in the Grok model family. For teams building systems where agents collaborate, delegate, and coordinate, it provides a model specifically tuned for those interaction patterns. The beta status means you should plan for potential changes before committing to production use.
Copy link to headingFrequently Asked Questions
What makes Grok 4.20 Multi-Agent different from other Grok 4.20 models?
Grok 4.20 Multi-Agent is purpose-built for multi-agent orchestration. While the reasoning and non-reasoning variants target individual agent tasks, this model is optimized for workflows where multiple agents coordinate and collaborate.
What is the context window for Grok 4.20 Multi-Agent?
2M tokens.
Is Grok 4.20 Multi-Agent in beta?
Yes. Grok 4.20 Multi-Agent is currently in beta. Behavior, pricing, or availability may change before general availability.
What does Grok 4.20 Multi-Agent cost?
Current pricing is shown on this page. AI Gateway routes across providers, and rates may vary by provider.
How do I authenticate with Grok 4.20 Multi-Agent through Vercel AI Gateway?
Use your Vercel AI Gateway API key with
spacexai/grok-4.20-multi-agentas the model identifier. No separate SpaceXAI account is needed for gateway-managed access.Can I use Grok 4.20 Multi-Agent for single-agent workflows?
You can, but it's optimized for multi-agent patterns. For single-agent use cases, the Grok 4.20 Non-Reasoning or Reasoning variants are better choices.
Does Vercel AI Gateway support Zero Data Retention for Grok 4.20 Multi-Agent?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.