Google: Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to k…

google/gemini-4-argon-20261013

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

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

41–60 / 96

LMArena

1,545.886

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
2
sample size
12589
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1539.3386869243102
confidence upper
1552.4336887297131
Original result ↗

LMArena

1,545.493

source id
lmarena
leaderboard name
LMArena Text Style Control Multi Turn
dimension
style
metric
Arena rating
rank
2
sample size
2794
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1533.118940696394
confidence upper
1557.8679962818578
Original result ↗

LMArena

1,543.64

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts English
dimension
style
metric
Arena rating
rank
2
sample size
4804
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1534.0538031679432
confidence upper
1553.2264173055232
Original result ↗

LMArena

1,543.241

source id
lmarena
leaderboard name
LMArena Text Hard Prompts
dimension
general
metric
Arena rating
rank
2
sample size
12589
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1536.7503067751888
confidence upper
1549.7307589678187
Original result ↗

LMArena

1,542.969

source id
lmarena
leaderboard name
LMArena Text Industry Software And It Services
dimension
general
metric
Arena rating
rank
2
sample size
6887
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1534.9523416993868
confidence upper
1550.9850808525107
Original result ↗

LMArena

1,539.662

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
2
sample size
2848
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1527.6227557092066
confidence upper
1551.700898659739
Original result ↗

LMArena

1,539.551

source id
lmarena
leaderboard name
LMArena Text Hard Prompts English
dimension
general
metric
Arena rating
rank
2
sample size
4804
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1530.0712071842122
confidence upper
1549.0312684456817
Original result ↗

LMArena

1,538.965

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
2
sample size
301
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1501.7261318364974
confidence upper
1576.203804933326
Original result ↗

LMArena

1,537.179

source id
lmarena
leaderboard name
LMArena Text Instruction Following
dimension
general
metric
Arena rating
rank
2
sample size
7180
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1529.0536506351607
confidence upper
1545.3040684208147
Original result ↗

LMArena

1,534.267

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
2
sample size
5991
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1525.2594676115214
confidence upper
1543.2735770881313
Original result ↗

LMArena

1,533.673

source id
lmarena
leaderboard name
LMArena Text Factuality Longer Query
dimension
factuality
metric
Arena rating
rank
2
sample size
8748
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1527.1012766513427
confidence upper
1540.2444414262193
Original result ↗

LMArena

1,532.487

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
2
sample size
2848
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1520.4265413998396
confidence upper
1544.5471318517398
Original result ↗

LMArena

1,530.16

source id
lmarena
leaderboard name
LMArena Text Overall
dimension
general
metric
Arena rating
rank
2
sample size
19787
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1524.7221345271455
confidence upper
1535.597933491806
Original result ↗

LMArena

1,530.039

source id
lmarena
leaderboard name
LMArena Text Industry Medicine And Healthcare
dimension
general
metric
Arena rating
rank
2
sample size
1322
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1512.76223410109
confidence upper
1547.3153411638787
Original result ↗

LMArena

1,529.092

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
2
sample size
7454
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1521.2610069762993
confidence upper
1536.9231349840547
Original result ↗

LMArena

1,527.187

source id
lmarena
leaderboard name
LMArena Text Style Control Polish
dimension
style
metric
Arena rating
rank
2
sample size
309
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1491.4640527736433
confidence upper
1562.9095660881544
Original result ↗

LMArena

1,525.898

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
2
sample size
5991
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1516.8731032574424
confidence upper
1534.9225976041334
Original result ↗

LMArena

1,524.02

source id
lmarena
leaderboard name
LMArena Text Non English
dimension
general
metric
Arena rating
rank
2
sample size
12333
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1517.4994956335686
confidence upper
1530.5411280707012
Original result ↗

LMArena

1,523.686

source id
lmarena
leaderboard name
LMArena Text Industry Entertainment And Sports And Media
dimension
general
metric
Arena rating
rank
2
sample size
5372
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1514.1649337914478
confidence upper
1533.20626836212
Original result ↗

LMArena

1,522.378

source id
lmarena
leaderboard name
LMArena Text Style Control Overall
dimension
style
metric
Arena rating
rank
2
sample size
19787
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1516.9054927755265
confidence upper
1527.8504598427576
Original result ↗

Published prices

1–20 / 61

gemini-4-argon ↗

$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-argon ↗

$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-argon ↗

$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-argon ↗

$0.10

Inference provider
cloudflareWorkersAI
Platform
Google Vertex AI
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

google/gemini-4-argon ↗

$2.00

Inference provider
cloudflareWorkersAI
Platform
Google Vertex AI
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

google/gemini-4-argon ↗

$10.00

Inference provider
cloudflareWorkersAI
Platform
Google Vertex AI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)
Pricing via
Cloudflare AI Gateway

google/gemini-4-argon ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$0.19

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$2.00

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$10.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
google
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
google | google/gemini-4-argon
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

google/gemini-4-argon ↗

$0.05

Inference provider
vercelAIGatewayCatalog
Platform
google
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
google | google/gemini-4-argon
model_type
language
service_tier
flex
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–4 / 4

gemini-4-argon ↗

source model id
gemini-4-argon
hosting
gateway
platforms
  • Cheaper Inference
context length
1048576
max output tokens
1000000
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput
  • webSearch

google ↗

source model id
Gemini 4 Argon
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 Argon[^gemini-4-argon-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 Argon
excels_at
Thorough work that tests edge cases before finishing
task_area
Complex coding, agentic, and reasoning tasks
further_reading
[Gemini 4 Argon](https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-4-Argon-Model-Card.pdf)

Gemini 4 Argon ↗

source model id
google/gemini-4-argon
hosting
third-party
platforms
  • Google Vertex AI
context length
1048576
max output tokens
65536
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Gemini 4 Argon ↗

    source model id
    google/gemini-4-argon
    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

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    41 / 100

    source id
    stanfordFMTI
    canonical model id
    google/gemini-4-argon-20261013
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Google
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    41 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–8 / 8

    cloudflareWorkersAI ↗

    field
    context_length
    value
    1048576
    normalized value
    1048576
    scope
    source-model
    source id
    cloudflareWorkersAI
    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

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    65536
    normalized value
    65536
    scope
    source-model
    source id
    cloudflareWorkersAI
    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

    1–14 / 14

    Google · Model reference ↗

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Vercel AI Gateway · Model page ↗

    GitHub · Documentation ↗

    GitHub · Source snapshot ↗

    api.cheaperinference.com · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    Epoch AI · Catalog ↗

    GitHub · Catalog ↗

    LMArena · Catalog ↗

    OpenRouter · Catalog ↗

    OpenRouter · Catalog ↗

    Vercel AI Gateway · Catalog ↗

    Source links

    1–10 / 10

    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