GeekRadar / The comparison desk

COMPARE.

AI models

xai

Grok 4.3

AI model Released Apr 17, 2026

API mode: Chat^*
Context window: 1,000,000 tokens
Maximum output: 30,000 tokens
Open weights: No

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Grok 4.3 1396.9 Grok 4.3 · 95% interval 1393.3–1400.5 · 71,287 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Grok 4.3

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

5 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Grok 4.3 88.8^*% Approx. 95% interval: 85.0–92.7% · 2026-06-17

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Grok 4.3 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Grok 4.3 42.8^*% Approx. 95% interval: 37.1–48.6% · 2026-06-17

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Grok 4.3 33.2^*% Approx. 95% interval: 30.3–36.1% · 2026-08-27

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Grok 4.3 93.3^*% Approx. 95% interval: 87.4–99.3% · 2026-06-17

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

Grok 4.3 14.6^*% Approx. 95% interval: 3.7–25.6% · 2026-06-17

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Test version

Arena text preference / chinesehuman preference · 2026-10-28 · rating

Grok 4.3

1,420.79 rating

Confidence interval: 1,411.23 – 1,430.35

4496 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Grok 4.3

1,414.43 rating

Confidence interval: 1,408.85 – 1,420.02

19961 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Grok 4.3

1,379.55 rating

Confidence interval: 1,373.06 – 1,386.03

13162 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Grok 4.3

1,404.10 rating

Confidence interval: 1,399.41 – 1,408.79

32779 votes

Oct 28, 2026

Category: english
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Grok 4.3

1,377.75 rating

Confidence interval: 1,373.04 – 1,382.46

54736 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Grok 4.3

1,384.85 rating

Confidence interval: 1,377.07 – 1,392.63

7534 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Grok 4.3

1,410.96 rating

Confidence interval: 1,397.31 – 1,424.61

2567 votes

Oct 28, 2026

Category: french
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Grok 4.3

1,397.21 rating

Confidence interval: 1,378.07 – 1,416.35

1044 votes

Oct 28, 2026

Category: german
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Grok 4.3

1,396.48 rating

Confidence interval: 1,392.17 – 1,400.78

47647 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Grok 4.3

1,401.69 rating

Confidence interval: 1,396.27 – 1,407.10

22452 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Grok 4.3

1,380.96 rating

Confidence interval: 1,374.74 – 1,387.17

14225 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Grok 4.3

1,370.11 rating

Confidence interval: 1,364.20 – 1,376.03

17230 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Grok 4.3

1,385.51 rating

Confidence interval: 1,376.81 – 1,394.20

5787 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Grok 4.3

1,399.49 rating

Confidence interval: 1,392.96 – 1,406.01

11786 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Grok 4.3

1,397.01 rating

Confidence interval: 1,386.86 – 1,407.16

3932 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Grok 4.3

1,384.15 rating

Confidence interval: 1,375.11 – 1,393.20

5311 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Grok 4.3

1,415.70 rating

Confidence interval: 1,410.75 – 1,420.65

28541 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Grok 4.3

1,384.62 rating

Confidence interval: 1,378.91 – 1,390.33

18605 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Grok 4.3

1,365.71 rating

Confidence interval: 1,360.48 – 1,370.95

25095 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Grok 4.3

1,378.81 rating

Confidence interval: 1,356.79 – 1,400.84

861 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Grok 4.3

1,354.54 rating

Confidence interval: 1,335.44 – 1,373.64

1125 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Grok 4.3

1,392.55 rating

Confidence interval: 1,387.61 – 1,397.49

33161 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Grok 4.3

1,387.13 rating

Confidence interval: 1,376.43 – 1,397.84

3408 votes

Oct 28, 2026

Category: math
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Grok 4.3

1,405.71 rating

Confidence interval: 1,399.21 – 1,412.20

12843 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Grok 4.3

1,385.35 rating

Confidence interval: 1,380.86 – 1,389.84

38507 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Grok 4.3

1,396.88 rating

Confidence interval: 1,393.27 – 1,400.48

71287 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Grok 4.3

1,398.05 rating

Confidence interval: 1,380.56 – 1,415.55

1200 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Grok 4.3

1,398.53 rating

Confidence interval: 1,390.91 – 1,406.14

7486 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Grok 4.3

1,398.42 rating

Confidence interval: 1,383.94 – 1,412.89

2007 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Grok 4.3
Evaluation type: human preference

Arena text preference / chinesehuman preference · 2026-10-15 · rating

Grok 4.3

1,421.46 rating

Confidence interval: 1,411.92 – 1,431.00

4520 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

Grok 4.3

1,414.75 rating

Confidence interval: 1,409.16 – 1,420.35

19950 votes

Oct 15, 2026

Category: coding
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Grok 4.3

1,379.75 rating

Confidence interval: 1,373.27 – 1,386.24

13226 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

Grok 4.3

1,404.10 rating

Confidence interval: 1,399.40 – 1,408.79

32785 votes

Oct 15, 2026

Category: english
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Grok 4.3

1,377.74 rating

Confidence interval: 1,373.03 – 1,382.46

54777 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

Grok 4.3

1,384.56 rating

Confidence interval: 1,376.77 – 1,392.36

7539 votes

Oct 15, 2026

Category: expert
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

Grok 4.3

1,411.80 rating

Confidence interval: 1,398.13 – 1,425.47

2581 votes

Oct 15, 2026

Category: french
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

Grok 4.3

1,394.91 rating

Confidence interval: 1,375.70 – 1,414.13

1043 votes

Oct 15, 2026

Category: german
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Grok 4.3

1,396.52 rating

Confidence interval: 1,392.22 – 1,400.83

47680 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Grok 4.3

1,401.73 rating

Confidence interval: 1,396.31 – 1,407.14

22457 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Grok 4.3

1,381.19 rating

Confidence interval: 1,374.97 – 1,387.40

14233 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Grok 4.3

1,370.73 rating

Confidence interval: 1,364.81 – 1,376.65

17244 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Grok 4.3

1,385.58 rating

Confidence interval: 1,376.88 – 1,394.28

5796 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Grok 4.3

1,399.37 rating

Confidence interval: 1,392.84 – 1,405.89

11796 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Grok 4.3

1,397.19 rating

Confidence interval: 1,387.04 – 1,407.35

3938 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Grok 4.3

1,383.79 rating

Confidence interval: 1,374.74 – 1,392.84

5323 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Grok 4.3

1,415.92 rating

Confidence interval: 1,410.97 – 1,420.88

28538 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Grok 4.3

1,384.75 rating

Confidence interval: 1,379.04 – 1,390.46

18665 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Grok 4.3

1,365.70 rating

Confidence interval: 1,360.46 – 1,370.94

25136 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

Grok 4.3

1,378.73 rating

Confidence interval: 1,356.49 – 1,400.97

854 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

Grok 4.3

1,355.22 rating

Confidence interval: 1,336.13 – 1,374.31

1130 votes

Oct 15, 2026

Category: korean
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Grok 4.3

1,392.71 rating

Confidence interval: 1,387.77 – 1,397.66

33219 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

Grok 4.3

1,387.19 rating

Confidence interval: 1,376.49 – 1,397.89

3416 votes

Oct 15, 2026

Category: math
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Grok 4.3

1,405.62 rating

Confidence interval: 1,399.13 – 1,412.11

12856 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Grok 4.3

1,385.43 rating

Confidence interval: 1,380.94 – 1,389.92

38561 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

Grok 4.3

1,396.92 rating

Confidence interval: 1,393.31 – 1,400.53

71347 votes

Oct 15, 2026

Category: overall
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

Grok 4.3

1,397.77 rating

Confidence interval: 1,380.26 – 1,415.29

1201 votes

Oct 15, 2026

Category: polish
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

Grok 4.3

1,398.73 rating

Confidence interval: 1,391.12 – 1,406.35

7507 votes

Oct 15, 2026

Category: russian
Evaluated configuration: grok-4.3
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

Grok 4.3

1,398.99 rating

Confidence interval: 1,384.48 – 1,413.51

2009 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: grok-4.3
Evaluation type: human preference

Run it locally

Inference · memory estimate

Grok 4.3

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Grok 4.3

Provider offer

Grok 4.3 / Pricing tiers 2

Provider / scope	Rate	Currency	Amount / unit
Google Vertex AIGrok 4.3Standard Token tier: 0 – 200,000	Cached input	USD	0.2 / 1M tokens
	Input	USD	1.25 / 1M tokens
	Output	USD	2.5 / 1M tokens
Google Vertex AIGrok 4.3Standard Token tier: 200,000 – No stated upper limit	Cached input	USD	0.4 / 1M tokens
	Input	USD	2.5 / 1M tokens
	Output	USD	5 / 1M tokens

Capabilities

Context window: 1,000,000 tokens
Maximum input: 1,000,000 tokens^*
Maximum output: 30,000 tokens
Reasoning: Yes
Tool calling: Yes
Structured output: Yes^*
Open weights: No
API mode: Chat^*
Image input: Yes^*
Prompt caching: Yes^*
Tool choice: Yes^*
Web search: Yes^*
Model license: Proprietary

Input modalities

text
image
pdf

Output modalities

text

System configuration

Detailed specifications

Specifications · 25 fields

cache read input token cost

2.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 200k tokens

4.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 200k tokens batches

3.2e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost batches

1.6e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per image token

1.25e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

1.25e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 200k tokens

2.5e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 200k tokens batches

2.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token batches

1.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

xai^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max input tokens

1,000,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max output tokens

1,000,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max tokens

1,000,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

chat^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token

2.5e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 200k tokens

5.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 200k tokens batches

4.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token batches

2.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports function calling

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports prompt caching

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports reasoning

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports response schema

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports tool choice

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports vision

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports web search

Yes^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.3^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

* Provisional data