GeekRadar / The comparison desk

COMPARE.

AI models

xai

Grok 4.6

AI model Released Aug 12, 2026

API mode: Chat^*
Context window: 500,000 tokens
Maximum output: 500,000 tokens
Open weights: No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Grok 4.6 156.9^* Grok 4.6 · 95% interval 155.1–159.4

Human preference · Arena

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

Grok 4.6 1428.5 Grok 4.6 (High) · 95% interval 1423.9–1433.2 · 33,824 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 4.6

Tested configuration Radar task score

60.5^* / 100

4/4 core tests · experimental v1

8 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Grok 4.6 93.2^*% Approx. 95% interval: 90.2–96.2% · 2026-08-14

Novel problem solving

Mystery Game Puzzles · 25%

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

Grok 4.6 34.0^*% Approx. 95% interval: 24.7–43.3% · 2026-08-14

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Grok 4.6 66.0^*% Approx. 95% interval: 60.5–71.5% · 2026-08-14

Factual answers

SimpleQA Verified · 25%

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

Grok 4.6 48.9^*% Approx. 95% interval: 45.8–52.0% · 2026-08-27

End-to-end software

MirrorCode · Separate result

Whole-program reimplementation with hidden tests; ML + Private, two languages. Budget: seven days and ten billion tokens per attempt.

Grok 4.6 41.1^*% Approx. 95% interval: 19.5–62.7% · 2026-10-21

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 4.6 99.2^*% Approx. 95% interval: 98.2–100.0% · 2026-08-14

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 4.6 31.7^*% Approx. 95% interval: 17.3–46.1% · 2026-08-14

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

Grok 4.6 40.0^*% Approx. 95% interval: 27.7–52.3% · 2026-09-24

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 4.6

1,472.53 rating

Confidence interval: 1,460.62 – 1,484.44

2761 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,464.29 rating

Confidence interval: 1,456.99 – 1,471.60

8394 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,426.43 rating

Confidence interval: 1,418.40 – 1,434.46

7492 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,433.95 rating

Confidence interval: 1,427.79 – 1,440.10

13532 votes

Oct 28, 2026

Category: english
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,419.39 rating

Confidence interval: 1,413.35 – 1,425.43

24960 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,466.10 rating

Confidence interval: 1,455.98 – 1,476.21

3835 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,451.76 rating

Confidence interval: 1,432.19 – 1,471.32

1047 votes

Oct 28, 2026

Category: french
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,415.59 rating

Confidence interval: 1,390.02 – 1,441.15

578 votes

Oct 28, 2026

Category: german
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,447.45 rating

Confidence interval: 1,442.08 – 1,452.81

21843 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,446.44 rating

Confidence interval: 1,439.18 – 1,453.70

8719 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,415.95 rating

Confidence interval: 1,407.77 – 1,424.12

6205 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,420.07 rating

Confidence interval: 1,412.59 – 1,427.54

8833 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,427.99 rating

Confidence interval: 1,416.37 – 1,439.61

2863 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,436.92 rating

Confidence interval: 1,428.41 – 1,445.43

5589 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,461.40 rating

Confidence interval: 1,447.86 – 1,474.94

2025 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,420.73 rating

Confidence interval: 1,407.90 – 1,433.56

2349 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,454.88 rating

Confidence interval: 1,448.61 – 1,461.15

12579 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,430.91 rating

Confidence interval: 1,423.80 – 1,438.03

9640 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,430.90 rating

Confidence interval: 1,424.37 – 1,437.42

11988 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,380.25 rating

Confidence interval: 1,354.03 – 1,406.46

611 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,390.79 rating

Confidence interval: 1,366.18 – 1,415.40

637 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,456.02 rating

Confidence interval: 1,449.92 – 1,462.13

15506 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,414.92 rating

Confidence interval: 1,400.28 – 1,429.56

1672 votes

Oct 28, 2026

Category: math
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,425.33 rating

Confidence interval: 1,416.43 – 1,434.24

5117 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,418.68 rating

Confidence interval: 1,413.27 – 1,424.10

20289 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,428.53 rating

Confidence interval: 1,423.89 – 1,433.16

33824 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,426.23 rating

Confidence interval: 1,400.55 – 1,451.90

519 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,418.67 rating

Confidence interval: 1,409.08 – 1,428.26

4317 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,416.33 rating

Confidence interval: 1,397.25 – 1,435.41

989 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Grok 4.6 (High)
Evaluation type: human preference

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

Grok 4.6

1,475.06 rating

Confidence interval: 1,462.25 – 1,487.86

2314 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,465.32 rating

Confidence interval: 1,457.63 – 1,473.01

7222 votes

Oct 15, 2026

Category: coding
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,426.90 rating

Confidence interval: 1,418.42 – 1,435.37

6434 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,432.54 rating

Confidence interval: 1,426.11 – 1,438.96

11735 votes

Oct 15, 2026

Category: english
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,418.46 rating

Confidence interval: 1,412.13 – 1,424.79

21412 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,467.78 rating

Confidence interval: 1,457.04 – 1,478.52

3311 votes

Oct 15, 2026

Category: expert
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,456.92 rating

Confidence interval: 1,435.45 – 1,478.40

840 votes

Oct 15, 2026

Category: french
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,431.86 rating

Confidence interval: 1,404.76 – 1,458.95

507 votes

Oct 15, 2026

Category: german
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,446.94 rating

Confidence interval: 1,441.30 – 1,452.57

18782 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,444.42 rating

Confidence interval: 1,436.84 – 1,451.99

7574 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,416.07 rating

Confidence interval: 1,407.48 – 1,424.66

5368 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,421.43 rating

Confidence interval: 1,413.57 – 1,429.29

7591 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,427.04 rating

Confidence interval: 1,414.72 – 1,439.36

2481 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,437.22 rating

Confidence interval: 1,428.23 – 1,446.22

4815 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,464.12 rating

Confidence interval: 1,449.47 – 1,478.78

1710 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,420.87 rating

Confidence interval: 1,407.27 – 1,434.46

2044 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,456.63 rating

Confidence interval: 1,450.07 – 1,463.19

10857 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,428.68 rating

Confidence interval: 1,421.21 – 1,436.14

8265 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,430.58 rating

Confidence interval: 1,423.75 – 1,437.41

10340 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,380.47 rating

Confidence interval: 1,351.60 – 1,409.34

497 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,395.77 rating

Confidence interval: 1,369.94 – 1,421.60

567 votes

Oct 15, 2026

Category: korean
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,454.89 rating

Confidence interval: 1,448.50 – 1,461.27

13401 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,416.35 rating

Confidence interval: 1,400.56 – 1,432.14

1421 votes

Oct 15, 2026

Category: math
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,423.93 rating

Confidence interval: 1,414.45 – 1,433.41

4363 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,418.89 rating

Confidence interval: 1,413.18 – 1,424.60

17226 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,427.77 rating

Confidence interval: 1,422.91 – 1,432.62

28965 votes

Oct 15, 2026

Category: overall
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,429.51 rating

Confidence interval: 1,401.93 – 1,457.10

436 votes

Oct 15, 2026

Category: polish
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,421.79 rating

Confidence interval: 1,411.54 – 1,432.03

3634 votes

Oct 15, 2026

Category: russian
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

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

Grok 4.6

1,403.71 rating

Confidence interval: 1,382.58 – 1,424.85

789 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: grok-4.6-high
Evaluation type: human preference

Run it locally

Inference · memory estimate

Grok 4.6

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 4.6

Provider offer

Grok 4.6 / Pricing tiers 3

Provider / scope	Rate	Currency	Amount / unit
Google Vertex AIGrok 4.6Standard Token tier: 0 – 200,000	Cached input	USD	0.5 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	6 / 1M tokens
Google Vertex AIGrok 4.6Standard Token tier: 200,000 – No stated upper limit	Cached input	USD	1 / 1M tokens
	Input	USD	4 / 1M tokens
	Output	USD	12 / 1M tokens
xAIgrok-4.6Standard	Cached input	USD	0.5 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	6 / 1M tokens

Capabilities

Context window: 500,000 tokens
Maximum input: 500,000 tokens^*
Maximum output: 500,000 tokens
Reasoning: Yes
Tool calling: Yes
Structured output: Yes^*
Open weights: No
Knowledge cutoff: 2026-02-01
API mode: Chat^*
Image input: Yes^*
Prompt caching: Yes^*
Tool choice: Yes^*
Web search: Yes^*
Model license: Proprietary

Input modalities

text
image

Output modalities

text

System configuration

Detailed specifications

Specifications · 19 fields

cache read input token cost

5.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

1.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

2.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

2.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

4.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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-4.6^*
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

500,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

500,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

500,000^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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-4.6^*
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

6.0e-6^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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

1.2e-5^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.6^*
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-4.6^*
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-4.6^*
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-4.6^*
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-4.6^*
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-4.6^*
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-4.6^*
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-4.6^*
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