Skip to content
AI Atlas
ModelActiveIdentity probable

Grok 4.20 Multi-Agent

xAIfamily · Grok 4.20docs.x.ai/developers/models/grok-4.20-multi-agen

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...

Open in Graph
data quality57

Updated 2 h ago · first seen 11 Sept 2026

model_01M294WW227TBTN9Q3PY5N8PCX

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
None recordedofficial_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
grok-4.20-multi-agent-0309x-ai/grok-4.20-multi-agentIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Official page
docs.x.ai/developers/models/grok-4.20-multi-agent-0309

Source:xAI — docsT1observed 12 h agohigh

API model id

Source:xAI — docsT1observed 12 h agohigh

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Architecture

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Capabilities

Modalities

Modalities
imagetext
Input
textimage
Output
text

Capabilities

  • Tool calling

    Yes

    xAI — docs · T1

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:xAI — docsT1observed 12 h agohigh

Max output

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Providers & Pricing3

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MBatch in / outNative unitsStatusObservedSource
OpenRoutercheapest outputx-ai/grok-4.20-multi-agent2Mout 1.8M$0.20——active4 min agosince 12 Sept 2026openrouter.aiT2
xAI APIgrok-4.20-multi-agent-03091M$0.20$1 / $2long_context_input_per_mtok=2.5long_context_output_per_mtok=5long_context_cached_input_per_mtok=0.4active5 min agosince 11 Sept 2026docs.x.aiT1
xAI APIx-ai/grok-4.20-multi-agent2Mout 1.8M$0.20——active4 h agosince 11 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of Grok 4.20 Multi-Agent$0$1$2$3Sept 26Sept 26Sept 26Sept 26Sept 26xAI API: first observed → $2.5 · 11 Sept 2026OpenRouter: first observed → $2.5 · 12 Sept 2026
  • xAI API
  • OpenRouter
  • OpenRouterfirst observed $2.512 Sept 2026
  • xAI APIfirst observed $2.511 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of Grok 4.20 Multi-Agent$0$0.50$1$1.5Sept 26Sept 26Sept 26Sept 26Sept 26xAI API: first observed → $1.25 · 11 Sept 2026OpenRouter: first observed → $1.25 · 12 Sept 2026
  • xAI API
  • OpenRouter
  • OpenRouterfirst observed $1.2512 Sept 2026
  • xAI APIfirst observed $1.2511 Sept 2026

Versions & Artifacts0

Version history

Context window1 change

11 Sept 2026→11 Sept 2026current

Knowledge cutofffirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline3

Full timeline →
  • Capabilities changedModelGrok 4.20 Multi-AgentxAI

    Grok 4.20 Multi-Agent: modalities changed from ["document", "image", "text"] to ["image", "text"]

    Modalitiesdocument, image, text→image, textxai
    docs.x.ai
  • Listed by providerModelGrok 4.20 Multi-AgentxAI

    OpenRouter lists Grok 4.20 Multi-Agent at $1.25 in / $2.5 out per 1M tokens

    openrouter
    openrouter.ai
  • Capabilities changedModelGrok 4.20 Multi-AgentxAI

    Grok 4.20 Multi-Agent: modalities changed from ["image", "text"] to ["document", "image", "text"]

    Modalitiesimage, text→document, image, textopenrouter
    openrouter.ai

Change history41

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 11 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 11 Sept 2026 21 claims in force

Family
Grok
Release date
31 Mar 2026
Context window
1M tokens
Max output
1.8M tokens
Knowledge cutoff
Sept 2025
Modalities
image, text
Input modalities
text, image
Output modalities
text
Tokenizer
Grok
API model id
grok-4.20-multi-agent-0309
Batch api
Yes
File input
Yes
Openrouter id
x-ai/grok-4.20-multi-agent
Reasoning
Yes
Regions
us-east-1, us-west-2
Structured output
Yes
Supported parameters
include_reasoning, logprobs, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, temperature, top_logprobs, top_p
Tool calling
Yes
Vision
Yes
41 claims · 22 properties14 conflicting

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
Grok → currentcurrentxAI — docsT1highdeterministic

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
31 Mar 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Context windowcontext_length7conflicting claims

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
2M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
2M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
2M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
2M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
2M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1M tokens → currentcurrentxAI — docsT1conflicteddeterministic
2M tokens → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
1.8M tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
ValueValid from → toStatusSourceConfidenceExtractor
Sept 2025 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities4conflicting claims

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
document, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentcurrentxAI — docsT1conflicteddeterministic
document, image, text → supersededOpenRouter public model & pricing listingT2mediumdeterministic
image, text → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input5conflicting claims

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
document, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
text, image → currentcurrentxAI — docsT1conflicteddeterministic
image, text → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
Grok → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

API model idapi_model_id1

Claim history for API model id
ValueValid from → toStatusSourceConfidenceExtractor
grok-4.20-multi-agent-0309 → currentcurrentxAI — docsT1highdeterministic

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://docs.x.ai/developers/models/grok-4.20-multi-agent-0309 → currentcurrentxAI — docsT1highdeterministic

Batch apibatch_api1

Claim history for Batch api
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentxAI — docsT1highdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
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... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

File inputfile_input1

Claim history for File input
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
x-ai/grok-4.20-multi-agent → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
31 Mar 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Regionsregions1

Claim history for Regions
ValueValid from → toStatusSourceConfidenceExtractor
us-east-1, us-west-2 → currentcurrentxAI — docsT1highdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
include_reasoning, logprobs, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, temperature, top_logprobs, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling7conflicting claims

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
No → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
No → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
No → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
No → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
No → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentcurrentxAI — docsT1conflicteddeterministic
No → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Visionvision1

Claim history for Vision
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

22

Source tiers

T1T29 / 13

Freshest observation

2 h ago

Conflicts

14 flagged

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
xAI — docsdocs.x.ai/developers/models/grok-4.20-multi-agent-0309.md model_pageT1· Official4 min ago1
xAI — docsdocs.x.ai/developers/models model_docsT1· Official5 min ago10
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary4 min ago11

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (57/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →