SpaceXAI: Grok 4.3

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factu…

x-ai/grok-4.3-20260430

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.

It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
1000000
Published model ID
grok-4.3
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

1–20 / 116

LMArena

1,193.792

source id
lmarena
leaderboard name
LMArena Search Style Control Overall
dimension
search
metric
Arena rating
rank
24
sample size
122703
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1188.8197596006398
confidence upper
1198.7650203795592
Original result ↗

LMArena

1,213.34

source id
lmarena
leaderboard name
LMArena Vision Style Control Entity Recognition
dimension
multimodal
metric
Arena rating
rank
25
sample size
150
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1169.2847783095103
confidence upper
1257.394667361257
Original result ↗

LMArena

1,175.196

source id
lmarena
leaderboard name
LMArena Search Factuality Overall
dimension
search
metric
Arena rating
rank
29
sample size
122703
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1171.3613580613815
confidence upper
1179.0304357521409
Original result ↗

LMArena

1,166.432

source id
lmarena
leaderboard name
LMArena Search Overall
dimension
search
metric
Arena rating
rank
30
sample size
122703
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1161.592254118257
confidence upper
1171.2710426644712
Original result ↗

LMArena

1,220.158

source id
lmarena
leaderboard name
LMArena Vision Entity Recognition
dimension
multimodal
metric
Arena rating
rank
35
sample size
150
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1176.037519086617
confidence upper
1264.2777684306816
Original result ↗

LMArena

1,414.087

source id
lmarena
leaderboard name
LMArena Text Factuality Japanese
dimension
factuality
metric
Arena rating
rank
38
sample size
561
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1394.8853826893492
confidence upper
1433.28894274693
Original result ↗

LMArena

1,388.673

source id
lmarena
leaderboard name
LMArena Text Factuality German
dimension
factuality
metric
Arena rating
rank
44
sample size
519
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1362.0470238135263
confidence upper
1415.2982890531962
Original result ↗

LMArena

1,366.229

source id
lmarena
leaderboard name
LMArena Text Factuality Korean
dimension
factuality
metric
Arena rating
rank
46
sample size
565
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1342.7696686058705
confidence upper
1389.687878424815
Original result ↗

LMArena

1,246.73

source id
lmarena
leaderboard name
LMArena Vision Style Control Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
47
sample size
2160
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1232.9253476438319
confidence upper
1260.53508255066
Original result ↗

LMArena

1,230.289

source id
lmarena
leaderboard name
LMArena Vision Style Control Humor
dimension
multimodal
metric
Arena rating
rank
57
sample size
1144
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1211.8729020981334
confidence upper
1248.7046765806813
Original result ↗

LMArena

1,247.411

source id
lmarena
leaderboard name
LMArena Vision Style Control English
dimension
multimodal
metric
Arena rating
rank
59
sample size
11546
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1239.4132920301756
confidence upper
1255.40966379736
Original result ↗

LMArena

1,375.503

source id
lmarena
leaderboard name
LMArena Webdev Image To Webdev
dimension
coding
metric
Arena rating
rank
61
sample size
5734
evaluated at
2026-11-10T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1365.7263388158165
confidence upper
1385.2789935410815
Original result ↗

LMArena

1,394.319

source id
lmarena
leaderboard name
LMArena Text Factuality Polish
dimension
factuality
metric
Arena rating
rank
62
sample size
723
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1372.6274422035615
confidence upper
1416.0114701088023
Original result ↗

LMArena

1,267.027

source id
lmarena
leaderboard name
LMArena Vision Style Control Diagram
dimension
multimodal
metric
Arena rating
rank
62
sample size
7735
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1258.897466484509
confidence upper
1275.1557507368589
Original result ↗

LMArena

1,277.563

source id
lmarena
leaderboard name
LMArena Vision Style Control Chinese
dimension
multimodal
metric
Arena rating
rank
63
sample size
1722
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1260.7541188724117
confidence upper
1294.3721619109074
Original result ↗

LMArena

1,241.653

source id
lmarena
leaderboard name
LMArena Vision Style Control Overall
dimension
multimodal
metric
Arena rating
rank
64
sample size
29224
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1235.9392702680761
confidence upper
1247.3663636689557
Original result ↗

LMArena

1,234.765

source id
lmarena
leaderboard name
LMArena Vision Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
64
sample size
2160
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1221.1221338003252
confidence upper
1248.4080992933
Original result ↗

LMArena

1,251.38

source id
lmarena
leaderboard name
LMArena Vision Style Control Ocr
dimension
multimodal
metric
Arena rating
rank
65
sample size
20543
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1245.6211246648843
confidence upper
1257.1383195653862
Original result ↗

LMArena

1,423.747

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
69
sample size
854
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1401.6736148438335
confidence upper
1445.8206108858785
Original result ↗

LMArena

1,222.955

source id
lmarena
leaderboard name
LMArena Vision Humor
dimension
multimodal
metric
Arena rating
rank
70
sample size
1144
evaluated at
2026-11-09T00:00:00.000Z
source model id
Grok 4.3
confidence lower
1204.5923993944714
confidence upper
1241.3169323915326
Original result ↗

Published prices

21–29 / 29

grok-4.3 ↗

$1.00

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

grok-4.3 ↗

$5.00

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-4.3 ↗

$2.50

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-4.3 ↗

$5.00

Inference provider
xAI
Platform
xAI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
input_tokens_gte
200000
Billing label
Output / 1M tokens

grok-4.3 ↗

$2.50

Inference provider
xAI
Platform
xAI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
input_tokens_lt
200000
Billing label
Output / 1M tokens

grok-4.3 ↗

$4.00

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-4.3 ↗

$2.00

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-4.3 ↗

$10.00

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-4.3 ↗

$5.00

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-4.3 ↗

source model id
grok-4.3
hosting
gateway
platforms
  • Cheaper Inference
context length
1000000
max output tokens
1000000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

Grok 4.3 ↗

source model id
grok-4.3
hosting
xai-hosted
platforms
  • xAI
context length
1000000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling
  • structuredOutputs
  • reasoning

Grok 4.3 ↗

source model id
publishers/xai/models/grok-4.3@001
hosting
vertex-managed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • image
  • text
output_modalities
  • text
capabilities
  • multimodal
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput

Grok 4.3 ↗

source model id
xai/grok-4.3
hosting
third-party
platforms
  • xAI
context length
1000000
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-4.3-20260430
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

1–6 / 6

cloudflareWorkersAI ↗

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

openRouter ↗

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

openRouter ↗

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

xAI ↗

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

openRouter ↗

field
max_output_tokens
value
900000
normalized value
900000
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
900000
normalized value
900000
scope
source-model
source id
openRouter
confidence
1

Original sources

1–13 / 13

Google Cloud · Model page ↗

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Google Cloud · Documentation ↗

xAI · Model documentation ↗

GitHub · Source snapshot ↗

api.cheaperinference.com · Source snapshot ↗

Cloudflare AI · Catalog ↗

GitHub · Catalog ↗

Google Cloud · Catalog ↗

LMArena · Catalog ↗

OpenRouter · Catalog ↗

xAI · Catalog ↗

Source links

1–8 / 8

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