GeekRadar / The comparison desk

COMPARE.

AI models

xai

Grok 4.5

AI model Released Jul 8, 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 4.5 154.4^* Grok 4.5 · 95% interval 152.8–156.6

Human preference · Arena

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

Grok 4.5 1447.6 Grok 4.5 · 95% interval 1443.3–1452.0 · 39,801 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 4.5

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

7 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Grok 4.5 93.4^*% Approx. 95% interval: 90.6–96.2% · 2026-07-08

Novel problem solving

Mystery Game Puzzles · 25%

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

Grok 4.5 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Grok 4.5 57.2^*% Approx. 95% interval: 51.4–62.9% · 2026-07-09

Factual answers

SimpleQA Verified · 25%

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

Grok 4.5 48.3^*% Approx. 95% interval: 45.2–51.4% · 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 4.5 32.2^*% Approx. 95% interval: 11.2–53.2% · 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 4.5 97.8^*% Approx. 95% interval: 95.3–100.0% · 2026-07-08

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 4.5 24.4^*% Approx. 95% interval: 11.1–37.7% · 2026-07-09

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 4.5 22.5^*% Approx. 95% interval: 12.0–33.0% · 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 4.5

1,494.30 rating

Confidence interval: 1,482.98 – 1,505.63

3036 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,474.02 rating

Confidence interval: 1,467.41 – 1,480.64

11123 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,441.87 rating

Confidence interval: 1,434.23 – 1,449.51

8215 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,452.66 rating

Confidence interval: 1,446.93 – 1,458.38

16168 votes

Oct 28, 2026

Category: english
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,445.74 rating

Confidence interval: 1,440.15 – 1,451.33

29858 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,464.58 rating

Confidence interval: 1,455.39 – 1,473.78

4708 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,456.75 rating

Confidence interval: 1,438.71 – 1,474.79

1283 votes

Oct 28, 2026

Category: french
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,445.63 rating

Confidence interval: 1,422.56 – 1,468.69

684 votes

Oct 28, 2026

Category: german
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,461.61 rating

Confidence interval: 1,456.58 – 1,466.63

26590 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,463.86 rating

Confidence interval: 1,457.21 – 1,470.51

10716 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,441.08 rating

Confidence interval: 1,433.60 – 1,448.57

7618 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,433.43 rating

Confidence interval: 1,426.50 – 1,440.37

10323 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,462.66 rating

Confidence interval: 1,451.75 – 1,473.56

3322 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,464.54 rating

Confidence interval: 1,456.68 – 1,472.40

6520 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,482.01 rating

Confidence interval: 1,468.83 – 1,495.19

2164 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,439.98 rating

Confidence interval: 1,428.41 – 1,451.56

2923 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,470.81 rating

Confidence interval: 1,465.04 – 1,476.59

15970 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,444.60 rating

Confidence interval: 1,437.85 – 1,451.34

10824 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,445.01 rating

Confidence interval: 1,438.96 – 1,451.07

14483 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,429.04 rating

Confidence interval: 1,401.89 – 1,456.20

544 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,402.52 rating

Confidence interval: 1,380.17 – 1,424.86

739 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,461.87 rating

Confidence interval: 1,456.22 – 1,467.52

19221 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,459.01 rating

Confidence interval: 1,444.82 – 1,473.19

1756 votes

Oct 28, 2026

Category: math
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,455.80 rating

Confidence interval: 1,447.77 – 1,463.83

6634 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,439.69 rating

Confidence interval: 1,434.59 – 1,444.80

23631 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,447.64 rating

Confidence interval: 1,443.31 – 1,451.97

39801 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,431.35 rating

Confidence interval: 1,407.87 – 1,454.84

630 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,449.81 rating

Confidence interval: 1,440.58 – 1,459.04

4584 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,450.58 rating

Confidence interval: 1,432.09 – 1,469.06

1077 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Grok 4.5
Evaluation type: human preference

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

Grok 4.5

1,494.64 rating

Confidence interval: 1,483.37 – 1,505.91

3066 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,473.98 rating

Confidence interval: 1,467.36 – 1,480.60

11116 votes

Oct 15, 2026

Category: coding
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,441.90 rating

Confidence interval: 1,434.28 – 1,449.52

8298 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,453.01 rating

Confidence interval: 1,447.28 – 1,458.74

16197 votes

Oct 15, 2026

Category: english
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,446.07 rating

Confidence interval: 1,440.48 – 1,451.67

29917 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,465.88 rating

Confidence interval: 1,456.68 – 1,475.08

4720 votes

Oct 15, 2026

Category: expert
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,456.59 rating

Confidence interval: 1,438.44 – 1,474.73

1274 votes

Oct 15, 2026

Category: french
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,448.24 rating

Confidence interval: 1,425.26 – 1,471.23

686 votes

Oct 15, 2026

Category: german
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,462.05 rating

Confidence interval: 1,457.02 – 1,467.07

26662 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,464.09 rating

Confidence interval: 1,457.44 – 1,470.74

10737 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,440.89 rating

Confidence interval: 1,433.40 – 1,448.38

7620 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,433.78 rating

Confidence interval: 1,426.85 – 1,440.71

10395 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,463.27 rating

Confidence interval: 1,452.41 – 1,474.14

3349 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,464.70 rating

Confidence interval: 1,456.84 – 1,472.55

6541 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,481.15 rating

Confidence interval: 1,467.94 – 1,494.37

2161 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,440.53 rating

Confidence interval: 1,428.98 – 1,452.09

2938 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,470.85 rating

Confidence interval: 1,465.07 – 1,476.64

15966 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,444.96 rating

Confidence interval: 1,438.21 – 1,451.70

10904 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,445.58 rating

Confidence interval: 1,439.52 – 1,451.64

14539 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,430.69 rating

Confidence interval: 1,403.18 – 1,458.21

530 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,405.75 rating

Confidence interval: 1,383.30 – 1,428.21

731 votes

Oct 15, 2026

Category: korean
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,462.59 rating

Confidence interval: 1,456.93 – 1,468.25

19283 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,459.04 rating

Confidence interval: 1,444.88 – 1,473.19

1766 votes

Oct 15, 2026

Category: math
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,456.00 rating

Confidence interval: 1,447.96 – 1,464.04

6632 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,439.82 rating

Confidence interval: 1,434.71 – 1,444.93

23697 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,447.97 rating

Confidence interval: 1,443.64 – 1,452.30

39896 votes

Oct 15, 2026

Category: overall
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,432.52 rating

Confidence interval: 1,409.00 – 1,456.05

628 votes

Oct 15, 2026

Category: polish
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,449.08 rating

Confidence interval: 1,439.87 – 1,458.29

4639 votes

Oct 15, 2026

Category: russian
Evaluated configuration: grok-4.5
Evaluation type: human preference

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

Grok 4.5

1,451.25 rating

Confidence interval: 1,432.75 – 1,469.75

1081 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: grok-4.5
Evaluation type: human preference

Run it locally

Inference · memory estimate

Grok 4.5

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 4.5

Provider offer

Grok 4.5 / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
xAIgrok-4.5Standard	Cached input	USD	0.3 / 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
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

3.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.5^*
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

6.0e-7^*

Scope and conditions

native_context

provider: xai^*
mode: chat^*
full_native_model_id: xai/grok-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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-4.5^*
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