GeekRadar / The comparison desk

COMPARE.

AI models

xai

Grok 4.7

AI model Released Sep 21, 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 4.7 154.6^* Grok 4.7 · 95% interval 152.6–157.1

Human preference · Arena

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

Grok 4.7 1398.1 Grok 4.7 (xHigh) · 95% interval 1392.4–1403.9 · 16,442 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 4.7

Tested configuration Radar task score

57.7^* / 100

4/4 core tests · experimental v1

7 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Grok 4.7 92.7^*% Approx. 95% interval: 89.7–95.8% · 2026-09-22

Novel problem solving

Mystery Game Puzzles · 25%

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

Grok 4.7 29.0^*% Approx. 95% interval: 20.1–37.9% · 2026-09-22

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Grok 4.7 53.0^*% Approx. 95% interval: 47.2–58.8% · 2026-09-22

Factual answers

SimpleQA Verified · 25%

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

Grok 4.7 56.0^*% Approx. 95% interval: 52.9–59.1% · 2026-09-22

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 4.7 98.1^*% Approx. 95% interval: 95.3–100.0% · 2026-09-22

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 4.7 17.1^*% Approx. 95% interval: 5.4–28.7% · 2026-09-22

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 4.7 20.8^*% Approx. 95% interval: 10.6–31.1% · 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 4.7

1,446.96 rating

Confidence interval: 1,430.10 – 1,463.82

1311 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,427.65 rating

Confidence interval: 1,417.19 – 1,438.10

3617 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,381.22 rating

Confidence interval: 1,370.35 – 1,392.10

3673 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,411.78 rating

Confidence interval: 1,403.58 – 1,419.98

6417 votes

Oct 28, 2026

Category: english
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,377.24 rating

Confidence interval: 1,369.58 – 1,384.89

11987 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,434.87 rating

Confidence interval: 1,419.71 – 1,450.02

1606 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,426.01 rating

Confidence interval: 1,400.77 – 1,451.24

605 votes

Oct 28, 2026

Category: french
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,375.89 rating

Confidence interval: 1,340.65 – 1,411.14

271 votes

Oct 28, 2026

Category: german
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,413.56 rating

Confidence interval: 1,406.62 – 1,420.49

10012 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,425.56 rating

Confidence interval: 1,415.52 – 1,435.60

3955 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,390.07 rating

Confidence interval: 1,378.27 – 1,401.87

2800 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,376.46 rating

Confidence interval: 1,366.34 – 1,386.57

4188 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,420.67 rating

Confidence interval: 1,404.21 – 1,437.13

1367 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,415.90 rating

Confidence interval: 1,404.13 – 1,427.68

2770 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,434.00 rating

Confidence interval: 1,414.98 – 1,453.03

951 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,395.84 rating

Confidence interval: 1,377.91 – 1,413.78

1160 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,419.98 rating

Confidence interval: 1,411.42 – 1,428.53

5721 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,393.27 rating

Confidence interval: 1,383.58 – 1,402.96

4599 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,406.28 rating

Confidence interval: 1,397.51 – 1,415.05

5493 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,356.59 rating

Confidence interval: 1,322.70 – 1,390.49

337 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,376.03 rating

Confidence interval: 1,338.24 – 1,413.82

257 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,414.90 rating

Confidence interval: 1,406.68 – 1,423.13

6802 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,412.86 rating

Confidence interval: 1,392.90 – 1,432.82

862 votes

Oct 28, 2026

Category: math
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,394.12 rating

Confidence interval: 1,381.54 – 1,406.71

2465 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,383.82 rating

Confidence interval: 1,376.90 – 1,390.73

9983 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,398.10 rating

Confidence interval: 1,392.36 – 1,403.85

16442 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,419.63 rating

Confidence interval: 1,381.71 – 1,457.55

228 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,394.39 rating

Confidence interval: 1,381.40 – 1,407.38

2216 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,403.54 rating

Confidence interval: 1,379.68 – 1,427.40

608 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Grok 4.7 (xHigh)
Evaluation type: human preference

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

Grok 4.7

1,452.70 rating

Confidence interval: 1,433.15 – 1,472.24

927 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,431.66 rating

Confidence interval: 1,419.55 – 1,443.76

2522 votes

Oct 15, 2026

Category: coding
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,386.69 rating

Confidence interval: 1,374.16 – 1,399.22

2589 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,412.27 rating

Confidence interval: 1,403.01 – 1,421.53

4571 votes

Oct 15, 2026

Category: english
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,379.47 rating

Confidence interval: 1,370.85 – 1,388.08

8355 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,437.38 rating

Confidence interval: 1,419.76 – 1,455.00

1115 votes

Oct 15, 2026

Category: expert
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,442.76 rating

Confidence interval: 1,411.84 – 1,473.68

385 votes

Oct 15, 2026

Category: french
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,353.31 rating

Confidence interval: 1,309.78 – 1,396.84

179 votes

Oct 15, 2026

Category: german
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,415.48 rating

Confidence interval: 1,407.73 – 1,423.23

7054 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,426.92 rating

Confidence interval: 1,415.36 – 1,438.48

2803 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,388.84 rating

Confidence interval: 1,375.26 – 1,402.42

1996 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,380.35 rating

Confidence interval: 1,368.69 – 1,392.02

2948 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,424.74 rating

Confidence interval: 1,406.28 – 1,443.21

1016 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,416.84 rating

Confidence interval: 1,403.40 – 1,430.28

1982 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,436.77 rating

Confidence interval: 1,414.95 – 1,458.60

660 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,399.29 rating

Confidence interval: 1,378.38 – 1,420.20

814 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,422.53 rating

Confidence interval: 1,412.81 – 1,432.24

4071 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,394.78 rating

Confidence interval: 1,383.61 – 1,405.96

3233 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,407.57 rating

Confidence interval: 1,397.52 – 1,417.63

3853 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,355.14 rating

Confidence interval: 1,312.88 – 1,397.41

225 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,385.07 rating

Confidence interval: 1,341.96 – 1,428.18

190 votes

Oct 15, 2026

Category: korean
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,416.08 rating

Confidence interval: 1,406.75 – 1,425.41

4785 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,412.34 rating

Confidence interval: 1,388.91 – 1,435.77

590 votes

Oct 15, 2026

Category: math
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,390.95 rating

Confidence interval: 1,376.35 – 1,405.55

1721 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,386.20 rating

Confidence interval: 1,378.46 – 1,393.93

6985 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,400.52 rating

Confidence interval: 1,394.10 – 1,406.95

11591 votes

Oct 15, 2026

Category: overall
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,411.34 rating

Confidence interval: 1,368.15 – 1,454.53

164 votes

Oct 15, 2026

Category: polish
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,399.92 rating

Confidence interval: 1,384.97 – 1,414.86

1552 votes

Oct 15, 2026

Category: russian
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

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

Grok 4.7

1,404.74 rating

Confidence interval: 1,376.35 – 1,433.13

422 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: grok-4.7-xhigh
Evaluation type: human preference

Run it locally

Inference · memory estimate

Grok 4.7

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 4.7

Provider offer

Grok 4.7 / Pricing tiers 3

Provider / scope	Rate	Currency	Amount / unit
Google Vertex AIGrok 4.7Standard 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 4.7Standard 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-4.7Standard	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: 2026-05
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 · 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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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-4.7^*
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