Inference
EN
xAI

Grok 4.1 Fast

Grok 4.1 Fast is a standard model from xAI. 9 benchmarks count toward its index, in 5 categories.

  • Closed weights
  • Standard
  • Input: text
  • Released 2025-11
RankedEnough results for an index.
IndexAll categories, out of 100.33.3±8.9Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.138/sMedian 67/s
First tokenSeconds to the first output token.0.5 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.20Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.50Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted41.1176 / 218
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.2 counted32.8198 / 227
MultimodalTasks with images and text.1 counted18.1—
KnowledgeFacts and expert knowledge.3 counted32.5234 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted23.1—
MathMath problems.None counted——

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Gert Labs Composite Game BenchmarkAgenticAbove fitFar above this model's index.47.3%25 / 52
τ²-Bench Tool-Agent-User EvaluationAgentic63.7%83 / 149
Critical Physics TasksReasoning0.0%150 / 214
Artificial Analysis GPQA DiamondKnowledge63.7%147 / 199
Artificial Analysis Humanity's Last ExamKnowledge5.1%174 / 222
Artificial Analysis IFBenchInstruction36.5%119 / 146
Artificial Analysis Long Context ReasoningReasoning31.3%179 / 217
Artificial Analysis Omniscience AccuracyKnowledge17.2%144 / 164
Artificial Analysis MMMU-ProMultimodal48.4%103 / 113
τ²-bench BankingAgentic13.1%26 / 28

Sources

BenchLMCC BY-NC 4.0Sierra ResearchMIT

History

5 releases
Index34.0 → 33.3
23 Oct 202612 Nov 2026
Output / 1M$0.50 → $0.50
23 Oct 202612 Nov 2026

Questions

How much does Grok 4.1 Fast cost?
$0.20 per 1M input tokens, $0.50 per 1M output tokens.
How good is Grok 4.1 Fast?
Its index is 33.3 out of 100. That is place 242 of 283 ranked models.
What is Grok 4.1 Fast best at?
Agentic: 41.1 out of 100, place 176 of 218.
How fast is Grok 4.1 Fast?
138 output tokens per second, 0.5 s to the first token.
What is the context window of Grok 4.1 Fast?
1M tokens.
Is Grok 4.1 Fast open source?
No. Its weights are not published.
When was Grok 4.1 Fast released?
November 2025.

Badge

Grok 4.1 Fast on Inference360: place 242 of 283, index 33.3
HTML
<a href="https://inference360.ai/models/grok-4-1-fast"><img src="https://inference360.ai/badges/grok-4-1-fast.svg" alt="Grok 4.1 Fast on Inference360: place 242 of 283, index 33.3" height="20"></a>
Markdown
[![Grok 4.1 Fast on Inference360: place 242 of 283, index 33.3](https://inference360.ai/badges/grok-4-1-fast.svg)](https://inference360.ai/models/grok-4-1-fast)

Compare with

Granite 4.2 3B33.2Nemotron 3 Nano 30B32.9Celeris-133.7Grok 4.1 Fast (Reasoning)47.3

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from xAI

All models
Grok 4.1 Fast (Reasoning)47.3Grok 4.1UnrankedGrok RealtimeUnrankedGrok 4 Fast (Reasoning)45.3Grok Code Fast 141.2