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

61–68 / 68

LMArena

0.184

source id
lmarena
leaderboard name
LMArena Agent Task Outcome Explicit Overall
dimension
agentic
metric
Arena score
rank
4
sample size
21726
evaluated at
2026-11-11T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
0.1726896444421728
confidence upper
0.19464429474096503
Original result ↗

LMArena

1,538.138

source id
lmarena
leaderboard name
LMArena Text Industry Mathematical
dimension
general
metric
Arena rating
rank
5
sample size
237
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
1498.4009333679242
confidence upper
1577.875119005405
Original result ↗

LMArena

1,523.295

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Mathematical
dimension
style
metric
Arena rating
rank
6
sample size
237
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
1483.478332468355
confidence upper
1563.1117120453323
Original result ↗

LMArena

1,522.441

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Life And Physical And Social Science
dimension
style
metric
Arena rating
rank
6
sample size
632
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
1498.176600722221
confidence upper
1546.705721419411
Original result ↗

LMArena

1,508.804

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Medicine And Healthcare
dimension
style
metric
Arena rating
rank
14
sample size
269
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
1471.2753792115027
confidence upper
1546.3328062418182
Original result ↗

LMArena

0.005

source id
lmarena
leaderboard name
LMArena Agent Tool Hallucination Overall
dimension
agentic
metric
Arena score
rank
27
sample size
58513
evaluated at
2026-11-11T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
0.003641095703080975
confidence upper
0.007073598431937046
Original result ↗

LMArena

-0.052

source id
lmarena
leaderboard name
LMArena Agent Bash Reliability Overall
dimension
general
metric
Arena score
rank
46
sample size
15198
evaluated at
2026-11-11T00:00:00.000Z
source model id
Gemini 4 Carbon (High)
confidence lower
-0.05869251226811831
confidence upper
-0.045691374826158176
Original result ↗

Published prices

1–20 / 64

gemini-4-carbon ↗

$0.05

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

gemini-4-carbon ↗

$0.90

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gemini-4-carbon ↗

$4.50

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

google/gemini-4-carbon ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-carbon ↗

$0.19

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-carbon ↗

$2.00

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-carbon ↗

$10.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

~google/gemini-pro-latest ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Google: Gemini 4 Carbon
slug
google/gemini-4-carbon
routing_alias
true

~google/gemini-pro-latest ↗

$0.19

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Google: Gemini 4 Carbon
slug
google/gemini-4-carbon
routing_alias
true

~google/gemini-pro-latest ↗

$0.000002

Inference provider
openRouter
Platform
OpenRouter
Unit
image
Currency
USD
Billing conditions
alias_target
name
Google: Gemini 4 Carbon
slug
google/gemini-4-carbon
routing_alias
true

~google/gemini-pro-latest ↗

$2.00

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Google: Gemini 4 Carbon
slug
google/gemini-4-carbon
routing_alias
true

~google/gemini-pro-latest ↗

$10.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Google: Gemini 4 Carbon
slug
google/gemini-4-carbon
routing_alias
true

Provider specifications & access

1–3 / 3

gemini-4-carbon ↗

source model id
gemini-4-carbon
hosting
gateway
platforms
  • Cheaper Inference
context length
1048576
max output tokens
524288
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput
  • webSearch

google ↗

source model id
Gemini 4 Carbon
hosting
copilot-subscription
platforms
  • GitHub Copilot
architecture
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

Gemini 4 Carbon ↗

source model id
google/gemini-4-carbon
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1000000
max output tokens
1000000
architecture
input_modalities
  • text
  • image
  • pdf
  • video
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput
  • webSearch
regions
  • eu
  • us

Source specification observations

1–8 / 8

openRouter ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
context_length
value
1000000
normalized value
1000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

openRouter ↗

field
max_output_tokens
value
943718
normalized value
943718
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
943718
normalized value
943718
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
943718
normalized value
943718
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
1000000
normalized value
1000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

1–8 / 8

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

GitHub · Documentation ↗

api.cheaperinference.com · Source snapshot ↗

LMArena · Catalog ↗

OpenRouter · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–6 / 6

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace