SpaceXAI: Grok 4.5

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

x-ai/grok-4.5-20260708

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
500000
Published model ID
grok-4.5
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Evaluations

1–20 / 114

LMArena

1,219.964

source id
lmarena
leaderboard name
LMArena Search Factuality Overall
dimension
search
metric
Arena rating
rank
8
sample size
105282
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1215.6797055136883
confidence upper
1224.2482606289445
Original result ↗

LMArena

1,215.818

source id
lmarena
leaderboard name
LMArena Search Overall
dimension
search
metric
Arena rating
rank
13
sample size
105282
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1210.0696225921777
confidence upper
1221.5660877163148
Original result ↗

LMArena

1,205.442

source id
lmarena
leaderboard name
LMArena Search Style Control Overall
dimension
search
metric
Arena rating
rank
16
sample size
105282
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1199.6609663221675
confidence upper
1211.2222787122419
Original result ↗

LMArena

1,470.346

source id
lmarena
leaderboard name
LMArena Text Factuality Spanish
dimension
factuality
metric
Arena rating
rank
19
sample size
892
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1450.7887915444294
confidence upper
1489.9034482620539
Original result ↗

LMArena

0.051

source id
lmarena
leaderboard name
LMArena Agent Bash Recovery Steps Overall
dimension
agentic
metric
Arena score
rank
20
sample size
47481
evaluated at
2026-10-08T00:00:00.000Z
source model id
Grok 4.5
confidence lower
0.03164929056965082
confidence upper
0.07107204515487764
Original result ↗

LMArena

1,450.764

source id
lmarena
leaderboard name
LMArena Text Factuality Polish
dimension
factuality
metric
Arena rating
rank
21
sample size
309
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1420.6861644884264
confidence upper
1480.8414041848673
Original result ↗

LMArena

1,279.12

source id
lmarena
leaderboard name
LMArena Vision Style Control Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
23
sample size
1208
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1260.8896126658854
confidence upper
1297.3495401740745
Original result ↗

LMArena

1,482.257

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Mathematical
dimension
factuality
metric
Arena rating
rank
24
sample size
1786
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1468.787560258841
confidence upper
1495.7264200031868
Original result ↗

LMArena

1,466.246

source id
lmarena
leaderboard name
LMArena Document Style Control Overall
dimension
productivity
metric
Arena rating
rank
24
sample size
7447
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1458.5663536619131
confidence upper
1473.9259265960568
Original result ↗

LMArena

1,290.721

source id
lmarena
leaderboard name
LMArena Vision Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
24
sample size
1208
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1272.4817721803204
confidence upper
1308.959379634512
Original result ↗

LMArena

1,280.443

source id
lmarena
leaderboard name
LMArena Vision Style Control Overall
dimension
multimodal
metric
Arena rating
rank
26
sample size
13991
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1273.5825821911058
confidence upper
1287.3024197081124
Original result ↗

LMArena

1,451.495

source id
lmarena
leaderboard name
LMArena Document Overall
dimension
productivity
metric
Arena rating
rank
27
sample size
7447
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1443.920149876864
confidence upper
1459.0695554717595
Original result ↗

LMArena

1,561.602

source id
lmarena
leaderboard name
LMArena Webdev Image To Webdev
dimension
coding
metric
Arena rating
rank
28
sample size
4561
evaluated at
2026-11-10T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1552.1228456499475
confidence upper
1571.0807094960137
Original result ↗

LMArena

1,288.018

source id
lmarena
leaderboard name
LMArena Vision Overall
dimension
multimodal
metric
Arena rating
rank
29
sample size
13991
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1281.191854226318
confidence upper
1294.8439569576512
Original result ↗

LMArena

1,491.34

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Mathematical
dimension
style
metric
Arena rating
rank
31
sample size
2108
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1478.0815814844134
confidence upper
1504.5990160366052
Original result ↗

LMArena

1,325.021

source id
lmarena
leaderboard name
LMArena Vision Style Control Chinese
dimension
multimodal
metric
Arena rating
rank
31
sample size
801
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1302.5693564338148
confidence upper
1347.4728646856574
Original result ↗

LMArena

1,304.123

source id
lmarena
leaderboard name
LMArena Vision Diagram
dimension
multimodal
metric
Arena rating
rank
31
sample size
3589
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1293.510041666414
confidence upper
1314.736340208292
Original result ↗

LMArena

1,293.076

source id
lmarena
leaderboard name
LMArena Vision Ocr
dimension
multimodal
metric
Arena rating
rank
31
sample size
9554
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1285.8494681375303
confidence upper
1300.3034875617284
Original result ↗

LMArena

1,290.159

source id
lmarena
leaderboard name
LMArena Vision Style Control Ocr
dimension
multimodal
metric
Arena rating
rank
31
sample size
9554
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1282.8912159171082
confidence upper
1297.4260040100746
Original result ↗

LMArena

1,263.699

source id
lmarena
leaderboard name
LMArena Vision Style Control Humor
dimension
multimodal
metric
Arena rating
rank
31
sample size
639
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.5
confidence lower
1239.635183174526
confidence upper
1287.762179435429
Original result ↗

Published prices

21–28 / 28

grok-4.5 ↗

$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

grok-4.5 ↗

$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

grok-4.5 ↗

$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

grok-4.5 ↗

$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

grok-4.5 ↗

$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

grok-4.5 ↗

$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

grok-4.5 ↗

$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

grok-4.5 ↗

$12.00

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_lt
200000
Billing label
Output / 1M tokens

Provider specifications & access

1–4 / 4

grok-4.5 ↗

source model id
grok-4.5
hosting
gateway
platforms
  • Cheaper Inference
context length
500000
max output tokens
500000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

Grok 4.5 ↗

source model id
grok-4.5
hosting
xai-hosted
platforms
  • xAI
context length
500000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling
  • structuredOutputs
  • reasoning

xai ↗

source model id
Grok 4.5
hosting
copilot-subscription
platforms
  • GitHub Copilot
architecture
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 4.5
    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 4.5
    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 4.5
excels_at
Complex problem-solving challenges, sophisticated reasoning
task_area
General-purpose coding and agent tasks
further_reading
[Grok 4.5 model card](https://media.x.ai/v1/website/card-7f81d41b.pdf)

Grok 4.5 ↗

source model id
xai/grok-4.5
hosting
third-party
platforms
  • xAI
context length
500000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

14 / 100

source id
stanfordFMTI
canonical model id
x-ai/grok-4.5-20260708
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

cloudflareWorkersAI ↗

field
context_length
value
500000
normalized value
500000
scope
source-model
source id
cloudflareWorkersAI
confidence
1

openRouter ↗

field
context_length
value
500000
normalized value
500000
scope
source-model
source id
openRouter
confidence
1

xAI ↗

field
context_length
value
500000
normalized value
500000
scope
source-model
source id
xAI
confidence
1

openRouter ↗

field
max_output_tokens
value
450000
normalized value
450000
scope
source-model
source id
openRouter
confidence
1

Original sources

1–12 / 12

xAI · Model reference ↗

OpenRouter · Model page ↗

GitHub · Documentation ↗

xAI · Model documentation ↗

GitHub · Source snapshot ↗

api.cheaperinference.com · Source snapshot ↗

Cloudflare AI · Catalog ↗

Epoch AI · Catalog ↗

GitHub · Catalog ↗

LMArena · Catalog ↗

OpenRouter · Catalog ↗

xAI · Catalog ↗

Source links

1–9 / 9

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