SpaceXAI: 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 sy…
x-ai/grok-4.20-multi-agent-20260309
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 across complex tasks.
Reasoning effort behavior:
- low / medium: 4 agents
- high / xhigh: 16 agents
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 2000000
- Knowledge cutoff
- 2025-09-01
- Published model ID
- grok-4.20-multi-agent-0309
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
21–40 / 107
1,447.155
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Creative Writing
- dimension
- style
- metric
- Arena rating
- rank
- 45
- sample size
- 11140
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1440.3793980802066
- confidence upper
- 1453.9310560992942
Original result ↗1,457.701
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 46
- sample size
- 7076
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1449.983103954683
- confidence upper
- 1465.4184658524766
Original result ↗1,453.418
- source id
- lmarena
- leaderboard name
- LMArena Text Polish
- dimension
- general
- metric
- Arena rating
- rank
- 47
- sample size
- 1314
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1437.2529138473797
- confidence upper
- 1469.5835921304633
Original result ↗1,448.843
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Spanish
- dimension
- factuality
- metric
- Arena rating
- rank
- 47
- sample size
- 1578
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1435.175075260633
- confidence upper
- 1462.5106296250315
Original result ↗1,465.262
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Spanish
- dimension
- style
- metric
- Arena rating
- rank
- 48
- sample size
- 1981
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1450.9612662014379
- confidence upper
- 1479.5633216696629
Original result ↗1,456.777
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 48
- sample size
- 1056
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1437.6174769342765
- confidence upper
- 1475.937348974058
Original result ↗1,471.057
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Overall
- dimension
- style
- metric
- Arena rating
- rank
- 49
- sample size
- 64252
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1467.3479628358393
- confidence upper
- 1474.7669275778644
Original result ↗1,463.796
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Russian
- dimension
- factuality
- metric
- Arena rating
- rank
- 49
- sample size
- 5610
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1455.8022895582635
- confidence upper
- 1471.7887596003968
Original result ↗1,478.149
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Exclude Ties
- dimension
- style
- metric
- Arena rating
- rank
- 50
- sample size
- 48621
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1473.2832597859374
- confidence upper
- 1483.0151242323925
Original result ↗1,483.204
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Medicine And Healthcare
- dimension
- factuality
- metric
- Arena rating
- rank
- 51
- sample size
- 3814
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1473.7308032061076
- confidence upper
- 1492.6779221974946
Original result ↗1,417.341
- source id
- lmarena
- leaderboard name
- LMArena Text Korean
- dimension
- general
- metric
- Arena rating
- rank
- 51
- sample size
- 998
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1397.7552332861644
- confidence upper
- 1436.9258101638563
Original result ↗1,440.88
- source id
- lmarena
- leaderboard name
- LMArena Text Non English
- dimension
- general
- metric
- Arena rating
- rank
- 52
- sample size
- 34959
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1436.359165556993
- confidence upper
- 1445.400932770448
Original result ↗1,466.692
- source id
- lmarena
- leaderboard name
- LMArena Text French
- dimension
- general
- metric
- Arena rating
- rank
- 53
- sample size
- 2234
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1452.638255792134
- confidence upper
- 1480.7456848966635
Original result ↗1,450.995
- source id
- lmarena
- leaderboard name
- LMArena Text Overall
- dimension
- general
- metric
- Arena rating
- rank
- 53
- sample size
- 64252
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1447.3055422525294
- confidence upper
- 1454.685370381177
Original result ↗1,250.538
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 53
- sample size
- 24357
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1244.4666651008795
- confidence upper
- 1256.6092232409362
Original result ↗1,474.286
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 54
- sample size
- 10550
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1467.606458041424
- confidence upper
- 1480.9658196043197
Original result ↗1,473.319
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control English
- dimension
- style
- metric
- Arena rating
- rank
- 54
- sample size
- 29292
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1468.422837554242
- confidence upper
- 1478.2145729102635
Original result ↗1,443.619
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Non English
- dimension
- factuality
- metric
- Arena rating
- rank
- 54
- sample size
- 34884
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1439.7049277177778
- confidence upper
- 1447.5323337350635
Original result ↗1,439.639
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Entertainment And Sports And Media
- dimension
- style
- metric
- Arena rating
- rank
- 54
- sample size
- 14007
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1433.3930571899054
- confidence upper
- 1445.8842429516033
Original result ↗1,502.356
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 55
- sample size
- 25324
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.20 Multi-Agent Beta (0309)
- confidence lower
- 1497.2371662764554
- confidence upper
- 1507.4739440356532
Original result ↗Published prices
1–20 / 22
$0.20
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$1.25
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$2.50
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
$0.40
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_gte
- 200000
- Billing label
- Cached input / 1M tokens
$0.20
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_lt
- 200000
- Billing label
- Cached input / 1M tokens
$0.32
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- interface
- Batch API
- input_tokens_gte
- 200000
- Billing label
- Cached input / 1M tokens
$0.16
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- interface
- Batch API
- input_tokens_lt
- 200000
- Billing label
- Cached input / 1M tokens
$0.80
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- billing_rule
- Only when response confirms service_tier=priority
- service_tier
- Priority
- input_tokens_gte
- 200000
- Billing label
- Cached input / 1M tokens
$0.40
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- billing_rule
- Only when response confirms service_tier=priority
- service_tier
- Priority
- input_tokens_lt
- 200000
- Billing label
- Cached input / 1M tokens
$2.50
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_gte
- 200000
- Billing label
- Input / 1M tokens
$1.25
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_lt
- 200000
- Billing label
- Input / 1M tokens
$2.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- interface
- Batch API
- input_tokens_gte
- 200000
- Billing label
- Input / 1M tokens
$1.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- interface
- Batch API
- input_tokens_lt
- 200000
- Billing label
- Input / 1M tokens
$5.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- billing_rule
- Only when response confirms service_tier=priority
- service_tier
- Priority
- input_tokens_gte
- 200000
- Billing label
- Input / 1M tokens
$2.50
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- billing_rule
- Only when response confirms service_tier=priority
- service_tier
- Priority
- input_tokens_lt
- 200000
- Billing label
- Input / 1M tokens
$5.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_gte
- 200000
- Billing label
- Output / 1M tokens
$2.50
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_lt
- 200000
- Billing label
- Output / 1M tokens
$4.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- interface
- Batch API
- input_tokens_gte
- 200000
- Billing label
- Output / 1M tokens
$2.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- interface
- Batch API
- input_tokens_lt
- 200000
- Billing label
- Output / 1M tokens
Provider specifications & access
1–2 / 2
- source model id
- grok-4.20-multi-agent
- hosting
- gateway
- context length
- 2000000
- max output tokens
- 2000000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- grok-4.20-multi-agent-0309
- hosting
- xai-hosted
- context length
- 1000000
- capabilities
- toolCalling
- structuredOutputs
- reasoning
Safety assessments
1–1 / 1
14 / 100
- source id
- stanfordFMTI
- canonical model id
- x-ai/grok-4.20-multi-agent-20260309
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- xAI
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 14 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–4 / 4
- field
- context_length
- value
- 2000000
- normalized value
- 2000000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- xAI
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-09-01
- normalized value
- 2025-09-01
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 1800000
- normalized value
- 1800000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models