x-AI/Grok-4-Fast

Name: x-AI/Grok-4-Fast
Brand: xai
SKU: xai/grok-4-fast

xai·xai/grok-4-fast·GA·Closed

Fast Grok model for responsive chat, reasoning, and tool-assisted work

Specs & pricing

Input / output per 1M tokens

Reference price

Price undisclosed

Lowest paid

No paid channels

Context

2,000,000

Output limit

2,000,000

Knowledge cutoff

—

Released / updated

2025-09-20 / 2025-09-20

Capabilities

✓ Reasoning✓ Tool useStructured output✓ Temperature✓ Attachments

Modalities

TextImageAudioVideo

Quality & performanceArtificial Analysis · Intelligence Index v4.3 · rep. tier Non-reasoning

Intelligence11.1

Value—

Coding—

Agentic—

Output speed—

TTFT—

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers0 with public prices

Priced only

Provider	Tier	Input	Output	Cache read	Cache write	Context	Output limit	Status
Qiniu	Gateway	—	—	—	—	2,000,000	2,000,000	hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Upstream provides no control info

1 / 1 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Input tokens / month

Output tokens / month

Cache hit rate

Common scenarios

This model has no public prices; can't estimate.

Price historyone sample accumulated per data sync

Input listOutput listMin blended

Artificial Analysis evaluations9 items

GPQA Diamond60.6%

Humanity's Last Exam4.5%

MMLU-Pro73.0%

LiveCodeBench40.1%

Terminal-Bench Hard12.1%

AIME 202541.3%

τ²-Bench Telecom63.7%

AA-LCR24.0%

IFBench37.7%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.