0

Grok 4.1 Fast

Grok 4.1 Fast is an AI model from xAI.

Publisher
xAI
Family
Grok
Input
Output
License
proprietary
Released
19 Nov 2025

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →
Weights
Closed
API only
Input
$0
/1M tok
Output
$0
/1M tok
Blended
$0
#1/ 499/1M · 3:1
Speed
0
#103/ 498tok/s

Price & speed via Artificial Analysis · ranked across tracked models

Reasoning effortIndexSpeed
Reasoning20.40 t/s
Non-reasoning11.30 t/s

Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers

Reported on 32 evals across 13 domains - best 100.0% on Medpt · #1 of 2

Reported eval scores

32
Medpt100
Agent Diff Bench62
Hanabi11.8
Infraresolutionbench80.2
MMLU-Pro85.4
Humanity's Last Exam (HLE)19.3
LiveBench64.7
LiveCodeBench82.2
τ²-bench (Tau²-bench)93.3
AIME 2025: Problems from the American Invitational Mathematics Examination89.3
ProofBench4
GPQA Diamond85.3
SciCode44.2
LiveBench - Language74.3
LiveBench - Reasoning80.2
Terminal-Bench (Hard)24.2
LiveBench - Coding69.6
IFBench52.7
LiveBench - Math83.7
LiveBench - Data Analysis52.2

Head-to-heads

29

benchmark comparisons against other models

vs GPT-5.230 shared evalsvs Claude Opus 4.529 shared evalsvs Claude Sonnet 4.528 shared evalsvs GPT-5 Mini26 shared evalsvs DeepSeek V3.226 shared evalsvs GPT-5.525 shared evalsvs Gemini 3.1 Pro Preview25 shared evalsvs Claude Opus 4.625 shared evalsvs GPT-5.425 shared evalsvs GPT-5 Nano24 shared evalsvs Claude Opus 4.824 shared evalsvs Claude 4 Sonnet24 shared evalsvs Kimi K2.524 shared evalsvs Claude Opus 4.724 shared evalsvs GLM 4.724 shared evalsvs Claude Fable 523 shared evalsvs GLM 5.123 shared evalsvs Claude Sonnet 4.622 shared evalsvs Gemini 2.5 Pro22 shared evalsvs GPT-5.4 Mini22 shared evalsvs Qwen3.6 Plus21 shared evalsvs GPT-520 shared evalsvs gpt-oss-120b20 shared evalsvs GPT-4o16 shared evalsvs GPT-4o-mini15 shared evalsvs GPT-4.1 Mini14 shared evalsvs GPT-4.1 Nano14 shared evalsvs GPT-4.113 shared evalsvs GPT-6 Astra10 shared evals