xAIMultimodalReleased 31 March 2026

Grok 4.20 Multi-Agent pricing, context and benchmark

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.

2M
Input context
1.80M
Output context
$1.25
Official input
$2.5
Official output
n/a
AA index

Everything that matters, in one table

Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.

ModelGrok 4.20 Multi-Agent
Model IDx-ai/grok-4.20-multi-agent
ProviderxAI
Release date31 March 2026
StatusGenerally available
Input context2,000,000 tokens
Output context1,800,000 tokens
Official input pricing$1.25 per 1M tokens
Official output pricing$2.5 per 1M tokens
Cache read pricingNot published
Market input pricing$1.25 per 1M (cheapest route)
Market output pricing$2.5 per 1M (cheapest route)
Highest route pricing$2.5 in, $5 out per 1M
Input modalitiestext · image · file
Output modalitiestext
Reasoning controlNot exposed
Tool supportText generation only
TokenizerGrok
Provider routes4 endpoints
Artificial Analysis indexNot published
SpeedNot published
Knowledge cutoffNot publicly stated

Input and output support

ModalityInputOutputBilled at
Text✓ yes✓ yes$1.25 in
Image✓ yesno$1.25 in
Audionononot supported
Videonononot supported
File (PDF)✓ yesno$1.25 in

What is Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is a variant of SpaceXAI’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...

Grok 4.20 Multi-Agent carries a 2M token window, uses the Grok tokenizer and is served by xAI. On Hoodgen it sits in the Multimodal tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.

Release and what changed from the previous version

Released31 March 2026

This is the only release of Grok 4.20 Multi-Agent on OpenRouter, released 31 March 2026. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.

Features and capabilities

◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
▤
Files and PDFs
Documents go in as files rather than pasted text, keeping layout and tables intact.

What can you do with Grok 4.20 Multi-Agent?

Document understanding
Screenshots, charts, scanned pages and PDFs read in the prompt.
Mixed media briefs
One thread holding text, images and files together.
Extraction
Schema constrained JSON out of messy inputs.
Research synthesis
Several sources condensed with the figures preserved.

Grok 4.20 Multi-Agent pricing

Official pricing

List price
$1.25 / 1M in
$2.5 / 1M out
  • 2M context
  • text, image, file input
Cheapest route
$1.25 / 1M in
$2.5 / 1M out
  • 4 routes on OpenRouter
  • What Hoodgen routes to first
  • Same model, lower bill
Highest route
$2.5 / 1M in
$5 / 1M out
  • Priority or premium tier
  • Best under load
  • Use for latency critical calls

Market pricing, every route

ProviderTierInputOutputCache readUptime 24h
xAIstandard$1.25$2.5$0.2100.0%
xAIstandard$1.25$2.5$0.229.4%
xAIpriority$2.5$5$0.4n/a
xAIpriority$2.5$5$0.4n/a

API pricing and cost calculator

RatePer callTotalCredits
Cheapest route$0.0161$8.077672
List price$0.0288$14.3813657
Highest route$0.0575$28.7527313

API and developer information

Model IDx-ai/grok-4.20-multi-agent
Endpointhttps://openrouter.ai/api/v1/chat/completions
Parametersprompt and max_tokens
StreamingYes, server sent events
Modality stringtext+image+file->text
Max prompt tokens2,000,000
Max completion tokens1,800,000
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.20-multi-agent",
    "messages": [{ "role": "user", "content": "Summarise this document." }],
    "max_tokens": 1024
  }'

Model limitations

Text only outputIt cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals.
Output cap1,800,000 tokens per request. Long deliverables have to be chunked.
Benchmarks not publishedArtificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here.
Knowledge cutoffThe provider does not state a fixed cutoff for every release. Verify very recent events against search.

Grok 4.20 Multi-Agent vs other xAI models

ModelContextInput /1MOutput /1MAA indexReleased
Grok 4.20 Multi-Agent2M$1.25$2.5n/a2026

Privacy and data policy

  • On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
  • Requests route through OpenRouter to xAI and are covered by that provider's API terms.
  • Do not paste secrets or personal data you would not send to any hosted model.

Grok 4.20 Multi-Agent questions, answered

Grok 4.20 Multi-Agent is a multimodal model from xAI, released 31 March 2026. Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.
✦

Start chatting with Grok 4.20 Multi-Agent

Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.