Google: Gemini 4 Carbon
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tok…
google/gemini-4-carbon-20261110
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium and high reasoning effort.
Specifications & capabilities
- Input
- audio, file, image, text, video
- Output
- text
- Context window · tokens
- 1048576
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Description source ↗Evaluations
1–20 / 68
1,614.081
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 428
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1584.678318531379
- confidence upper
- 1643.4846396358712
Original result ↗1,584.792
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Chinese
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 428
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1555.0446284488335
- confidence upper
- 1614.5395880445271
Original result ↗1,582.896
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 400
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1553.1887303694102
- confidence upper
- 1612.6023612963454
Original result ↗1,568.338
- source id
- lmarena
- leaderboard name
- LMArena Text Multi Turn
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 610
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1543.1111641472125
- confidence upper
- 1593.5652479057248
Original result ↗1,568.006
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Expert
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 400
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1538.3183687759756
- confidence upper
- 1597.6936601538569
Original result ↗1,567.229
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 1072
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1548.3774238190767
- confidence upper
- 1586.0804553314242
Original result ↗1,565.046
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Coding
- dimension
- factuality
- metric
- Arena rating
- rank
- 1
- sample size
- 1072
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1548.3593150274323
- confidence upper
- 1581.7335459592855
Original result ↗1,564.229
- source id
- lmarena
- leaderboard name
- LMArena Text Exclude Ties
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 3310
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1551.4908176335264
- confidence upper
- 1576.9671601567404
Original result ↗1,563.507
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 610
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1538.2448128991336
- confidence upper
- 1588.769370898453
Original result ↗1,563.408
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 1072
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1544.8169523426793
- confidence upper
- 1581.998537074507
Original result ↗1,560.416
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 635
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1536.2885460110044
- confidence upper
- 1584.5443815869012
Original result ↗1,552.56
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 1585
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1537.2852313249134
- confidence upper
- 1567.8341880897726
Original result ↗1,550.47
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 2675
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1538.4534840962856
- confidence upper
- 1562.485881052467
Original result ↗1,549.93
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Exclude Ties
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 3310
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1536.9931508570369
- confidence upper
- 1562.8672756317596
Original result ↗1,549.505
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 1585
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1534.1241558146091
- confidence upper
- 1564.886251748364
Original result ↗1,548.226
- source id
- lmarena
- leaderboard name
- LMArena Text Longer Query
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 1860
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1533.561014057639
- confidence upper
- 1562.8910801067664
Original result ↗1,548.082
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Russian
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 635
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1523.9660400954301
- confidence upper
- 1572.1987021883413
Original result ↗1,546.744
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Software And It Services
- dimension
- factuality
- metric
- Arena rating
- rank
- 1
- sample size
- 1585
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1533.1464836749126
- confidence upper
- 1560.3409570828203
Original result ↗1,546.301
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 2675
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1534.1852403856622
- confidence upper
- 1558.4162221284594
Original result ↗1,545.012
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 982
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Carbon (High)
- confidence lower
- 1525.3613343724592
- confidence upper
- 1564.663180650592
Original result ↗Published prices
61–64 / 64
$18.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- vertex
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- vertex | google/gemini-4-carbon
- model_type
- language
- service_tier
- priority
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$11.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- vertex
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- eu
- endpoint
- vertex | google/gemini-4-carbon
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$11.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- vertex
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- vertex | google/gemini-4-carbon
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- vertex
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- endpoint
- vertex | google/gemini-4-carbon
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–3 / 3
- source model id
- gemini-4-carbon
- hosting
- gateway
- context length
- 1048576
- max output tokens
- 524288
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- videoInput
- visionInput
- webSearch
- source model id
- Gemini 4 Carbon
- hosting
- copilot-subscription
- license
- CC-BY-4.0
- attribution
- GitHub and github/docs contributors
- plans
- max
- true
- pro
- false
- 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
- 10
- currency
- USD
- original
- tier
- Default
- input
- $2.00
- model
- Gemini 4 Carbon[^gemini-4-carbon-promo]
- output
- $10.00
- category
- Powerful
- provider
- google
- threshold
- Not applicable
- cached_input
- $0.10
- release_status
- GA
- threshold
- Not applicable
- cached_input
- 0.1
- footnote_restrictions
- true
- requires_subscription
- true
- comparison
- name
- Gemini 4 Carbon
- excels_at
- Secure code generation and security-focused work
- task_area
- Complex coding, agentic, and reasoning tasks
- further_reading
- Coming soon
- source model id
- google/gemini-4-carbon
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 1000000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- videoInput
- visionInput
- webSearch
Source specification observations
1–8 / 8
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 943718
- normalized value
- 943718
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 943718
- normalized value
- 943718
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 943718
- normalized value
- 943718
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Explore more models