xAI

Grok 4.20 Multi-Agent

CTX1M

Reasoning · Vision

Input$1.25/M

Output$2.50/M

Grok model for agentic tool use, reasoning, coding, and live assistance

PaidProprietary825/1044

Drag to turn

xAITextUncommon

Grok 4.20 Multi-Agent

Grok model for agentic tool use, reasoning, coding, and live assistance

grok-4.20-multi-agent-0309

Type: Text
Quality: Not rated yet
Context window: 1,000,000 tokens
Max output: 30,000 tokens
Input price: $1.25 / 1M tokens
Output price: $2.50 / 1M tokens
Cache read: $0.20 / 1M tokens
Cache write: —
Released: Mar 9, 2026
Knowledge cutoff: —
Takes in: Text, Image, PDF
Puts out: Text
Reasoning: Yes
Tool calling: No
Structured output: Yes
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Uncommon
Set number: 825/1044

Open xAI docs Where to run it 7 Evolution 1/5 Meet its creature Battle Gemini 3.5 Flash Lite

Weights aren’t public. Use is governed by xAI’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: docs.x.ai.

How good is it?

Public leaderboard scores for Grok 4.20 Multi-Agent, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Grok 4.20 Multi-Agent yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

7 providers sell Grok 4.20 Multi-Agent through an API. Prices are per million tokens, cheapest first.

CheapestKilo Gateway$1.25 in · $2.50 out
From the labxAI$1.25 in · $2.50 out

API providers

Provider	Input	Output	Context
Kilo GatewayCheapest paid`x-ai/grok-4.20-multi-agent`	$1.25	$2.50	2M
NanoGPT`x-ai/grok-4.20-multi-agent`	$1.25	$2.50	2M
OpenRouter`x-ai/grok-4.20-multi-agent`	$1.25	$2.50	2M
Vercel AI Gateway`spacexai/grok-4.20-multi-agent`	$1.25	$2.50	2M
xAIOfficial`grok-4.20-multi-agent-0309`	$1.25	$2.50	1M
Venice AI`grok-4-20-multi-agent`	$1.42	$2.83	2M
Poe`xai/grok-4.20-multi-agent`	$2.00	$6.00	128K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.