SpaceXAI: Grok 4.7
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work,…
x-ai/grok-4.7-20260916
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.
The model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 500000
- Knowledge cutoff
- 2026-05
- Published model ID
- grok-4.7
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗Evaluations
1–20 / 115
75.333%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Amazon Bedrock
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 6
- sample size
- 50
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 1
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-03T04:31:24.038Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 50
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.753333
- cost_per_task_usd
- 0.29315726000000003
- output_tokens_per_task
- 11166.84
- latency_seconds_per_task
- 206.11118
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 31
- benchmark_evaluation
- true
- openrouter_permaslug
- x-ai/grok-4.7-20260916
- source model id
- x-ai/grok-4.7-20260916
Original result ↗91.919%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Amazon Bedrock
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 8
- sample size
- 198
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 1
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-03T03:00:04.447Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 198
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.9191919999999999
- cost_per_task_usd
- 0.21825907575757575
- output_tokens_per_task
- 36106.61616161616
- latency_seconds_per_task
- 803.8660202020202
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 32
- benchmark_evaluation
- true
- openrouter_permaslug
- x-ai/grok-4.7-20260916
- source model id
- x-ai/grok-4.7-20260916
Original result ↗3.526%
- source id
- vercelAIGateway
- leaderboard name
- AI Gateway Text Spend Share
- dimension
- popularity
- metric
- Spend
- rank
- 8
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7
Original result ↗0.072
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Recovery Steps Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 11
- sample size
- 41891
- evaluated at
- 2026-10-08T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 0.061656550677604165
- confidence upper
- 0.08242011423509416
Original result ↗0.093
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Reliability Overall
- dimension
- general
- metric
- Arena score
- rank
- 15
- sample size
- 4538
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 0.08651189384859444
- confidence upper
- 0.0994944713473994
Original result ↗0.051
- source id
- lmarena
- leaderboard name
- LMArena Agent Task Outcome Explicit Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 15
- sample size
- 6338
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 0.018703282874454635
- confidence upper
- 0.08269592786474414
Original result ↗0.01
- source id
- lmarena
- leaderboard name
- LMArena Agent Tool Hallucination Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 15
- sample size
- 18416
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 0.009140288558722995
- confidence upper
- 0.010643512801283242
Original result ↗0.026
- source id
- lmarena
- leaderboard name
- LMArena Agent Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 17
- sample size
- 18939
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 0.010742738294300887
- confidence upper
- 0.04040098638117007
Original result ↗0.031
- source id
- lmarena
- leaderboard name
- LMArena Agent Praise Complaint Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 20
- sample size
- 3531
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- -0.01587315529341874
- confidence upper
- 0.07713826658518555
Original result ↗1,662.488
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev React
- dimension
- coding
- metric
- Arena rating
- rank
- 21
- sample size
- 4999
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1652.7331151208552
- confidence upper
- 1672.243751290794
Original result ↗1,588.756
- source id
- lmarena
- leaderboard name
- LMArena Webdev Image To Webdev
- dimension
- coding
- metric
- Arena rating
- rank
- 21
- sample size
- 1986
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1574.7755778467113
- confidence upper
- 1602.735575179076
Original result ↗1,640.952
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev
- dimension
- coding
- metric
- Arena rating
- rank
- 23
- sample size
- 8125
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1633.0000312771265
- confidence upper
- 1648.9047395950822
Original result ↗1,640.952
- source id
- lmarena
- leaderboard name
- LMArena Webdev Overall
- dimension
- coding
- metric
- Arena rating
- rank
- 23
- sample size
- 8125
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1633.0000312771265
- confidence upper
- 1648.9047395950822
Original result ↗1,635.575
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev Html
- dimension
- coding
- metric
- Arena rating
- rank
- 24
- sample size
- 1325
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1616.8016290291412
- confidence upper
- 1654.3479569313106
Original result ↗1,307.44
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 31
- sample size
- 889
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1287.5645260524213
- confidence upper
- 1327.316314388515
Original result ↗-0.023
- source id
- lmarena
- leaderboard name
- LMArena Agent Steerability Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 37
- sample size
- 11051
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- -0.04277559462214913
- confidence upper
- -0.0025289503272003036
Original result ↗1,478.877
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality French
- dimension
- factuality
- metric
- Arena rating
- rank
- 44
- sample size
- 540
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1452.6153243468739
- confidence upper
- 1505.1392152980693
Original result ↗1,291.641
- source id
- lmarena
- leaderboard name
- LMArena Vision Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 44
- sample size
- 889
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1271.7517737058065
- confidence upper
- 1311.5304866082577
Original result ↗1,283.849
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Diagram
- dimension
- multimodal
- metric
- Arena rating
- rank
- 50
- sample size
- 1520
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1267.6960033162914
- confidence upper
- 1300.0017679205093
Original result ↗1,466.784
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Polish
- dimension
- style
- metric
- Arena rating
- rank
- 52
- sample size
- 310
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Grok 4.7 (xHigh)
- confidence lower
- 1433.2058515555877
- confidence upper
- 1500.3624370342632
Original result ↗Published prices
21–40 / 43
$0.50
- 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
$0.80
- 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
$0.40
- 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
$2.00
- 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
$1.00
- 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
$1.10
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- US
- endpoint
- https://us.api.x.ai/v1
- input_tokens_gte
- 200000
- Billing label
- Cached input / 1M tokens
$0.55
- Inference provider
- xAI
- Platform
- xAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- US
- endpoint
- https://us.api.x.ai/v1
- input_tokens_lt
- 200000
- Billing label
- Cached input / 1M tokens
$4.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_gte
- 200000
- Billing label
- Input / 1M tokens
$2.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_lt
- 200000
- Billing label
- Input / 1M tokens
$3.20
- 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
$1.60
- 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
$8.00
- 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
$4.00
- 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_lt
- 200000
- Billing label
- Input / 1M tokens
$4.40
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- US
- endpoint
- https://us.api.x.ai/v1
- input_tokens_gte
- 200000
- Billing label
- Input / 1M tokens
$2.20
- Inference provider
- xAI
- Platform
- xAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- US
- endpoint
- https://us.api.x.ai/v1
- input_tokens_lt
- 200000
- Billing label
- Input / 1M tokens
$12.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_gte
- 200000
- Billing label
- Output / 1M tokens
$6.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- input_tokens_lt
- 200000
- Billing label
- Output / 1M tokens
$9.60
- 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
$4.80
- 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
$24.00
- Inference provider
- xAI
- Platform
- xAI
- Unit
- output_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
- Output / 1M tokens
Provider specifications & access
1–5 / 5
- source model id
- grok-4.7
- hosting
- xai-hosted
- context length
- 500000
- capabilities
- toolCalling
- structuredOutputs
- reasoning
- source model id
- Grok 4.7
- hosting
- copilot-subscription
- license
- CC-BY-4.0
- attribution
- GitHub and github/docs contributors
- plans
- max
- true
- pro
- true
- business
- true
- pro_plus
- true
- enterprise
- true
- clients
- vs
- true
- cli
- true
- xcode
- true
- dotcom
- false
- vscode
- true
- eclipse
- true
- jetbrains
- true
- access scope
- Published plan/client flags; account settings, organization policy and additional access conditions apply
- availability
- supported
- release status
- GA
- billing scope
- Copilot subscription usage; not an unconditional inference API rate
- billing rates
- tier
- Default
- unit
- tokens_per_million
- input
- 2
- output
- 6
- currency
- USD
- original
- tier
- Default
- input
- $2.00
- model
- Grok 4.7
- output
- $6.00
- category
- Versatile
- provider
- xai
- threshold
- ≤ 200K
- cached_input
- $0.50
- release_status
- GA
- threshold
- ≤ 200K
- cached_input
- 0.5
- footnote_restrictions
- false
- requires_subscription
- true
- tier
- Long context
- unit
- tokens_per_million
- input
- 4
- output
- 12
- currency
- USD
- original
- tier
- Long context
- input
- $4.00
- model
- Grok 4.7
- output
- $12.00
- category
- Versatile
- provider
- xai
- threshold
- > 200K
- cached_input
- $1.00
- release_status
- GA
- threshold
- > 200K
- cached_input
- 1
- footnote_restrictions
- false
- requires_subscription
- true
- comparison
- name
- Grok 4.7
- excels_at
- Complex problem-solving challenges, sophisticated reasoning
- task_area
- Agentic coding and complex, multistep workflows
- further_reading
- [Grok 4.7 model card](https://media.x.ai/v1/website/4p7card-5eccc980.pdf)
- source model id
- publishers/xai/models/grok-4.7@001
- hosting
- vertex-managed
- capabilities
- multimodal
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- source model id
- xai.grok-4.7
- hosting
- bedrock-managed
- source model id
- xai/grok-4.7
- hosting
- third-party
- context length
- 500000
Safety assessments
1–1 / 1
14 / 100
- source id
- stanfordFMTI
- canonical model id
- x-ai/grok-4.7-20260916
- 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
1–9 / 9
- field
- context_length
- value
- 500000
- normalized value
- 500000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 500000
- normalized value
- 500000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 500000
- normalized value
- 500000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 500000
- normalized value
- 500000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 500000
- normalized value
- 500000
- scope
- source-model
- source id
- xAI
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- May 2026
- normalized value
- 2026-05
- precision
- month
- scope
- source-model
- source id
- xAI
- confidence
- 1
- field
- max_output_tokens
- value
- 450000
- normalized value
- 450000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 450000
- normalized value
- 450000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 450000
- normalized value
- 450000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models