xAI model product
Grok 4.1
1 (Non-Thinking) is an xAI language model designed for fast responses without thinking tokens, with improvements in factual accuracy, interaction quality, safety, and refusal behavior.
Updated Sep 8, 2026. Default version: Grok-4.1
LLMBoard Score43.4Grok-4.1
Coverage0%1 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
Grok 4.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 4.1 Benchmark Results
Benchmark scores for Grok-4.1.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFActScore | Score97.03% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkEQ-Bench | Score1,585.00 points | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLMArena Text Leaderboard | Score1,465.00 points | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkCreative Writing v3 | Score85.43% | Rank07 | Participants13 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,459.16 rating | Rank40 | Participants210 | Percentile81.34% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,436.25 rating | Rank60 | Participants210 | Percentile71.77% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,430.55 rating | Rank77 | Participants121 | Percentile36.67% | EvidenceA | Evaluated |
Grok 4.1 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categorygerman | Rank14 | Rating / score1,425.66 | Votes713 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank24 | Rating / score1,405.36 | Votes499 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank24 | Rating / score1,474.63 | Votes1,999 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank25 | Rating / score1,432.36 | Votes1,127 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank29 | Rating / score1,450.03 | Votes1,999 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank29 | Rating / score1,418.58 | Votes1,378 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank30 | Rating / score1,484.89 | Votes4,359 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank31 | Rating / score1,465.47 | Votes1,236 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank35 | Rating / score1,406.90 | Votes1,127 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank35 | Rating / score1,462.14 | Votes12,692 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank38 | Rating / score1,445.86 | Votes1,236 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank38 | Rating / score1,470.85 | Votes28,224 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank38 | Rating / score1,465.06 | Votes48,043 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank38 | Rating / score1,471.49 | Votes4,853 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank40 | Rating / score1,459.16 | Votes66,382 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank42 | Rating / score1,443.91 | Votes38,151 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank43 | Rating / score1,477.84 | Votes10,649 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank44 | Rating / score1,475.94 | Votes1,738 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank46 | Rating / score1,428.85 | Votes12,466 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank47 | Rating / score1,430.59 | Votes9,649 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank47 | Rating / score1,418.32 | Votes685 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank48 | Rating / score1,474.34 | Votes38,004 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank48 | Rating / score1,446.13 | Votes1,941 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank50 | Rating / score1,493.69 | Votes4,850 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank50 | Rating / score1,479.41 | Votes16,480 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank50 | Rating / score1,460.66 | Votes11,989 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank51 | Rating / score1,410.73 | Votes9,649 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank51 | Rating / score1,416.12 | Votes6,350 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank51 | Rating / score1,488.15 | Votes23,975 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank54 | Rating / score1,447.36 | Votes28,224 | ObservationsN/A | Result date |
Grok 4.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $2 input, $10 output per 1M via 302.AI
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| Provider302.AI | Provider model IDgrok-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Grok 4.1 Runtime Performance
Provider-specific output speed and catalog latency for Grok-4.1. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderxAI | Output Speed100.00 tok/s | Catalog Latency0.70 s | Max Input256K | Max Output8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 4.1 Specifications
Technical details for the model's default version.
- Version
- Grok-4.1
- Released
- Nov 17, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 256K
- Max output
- 8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 4.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGrok-4.1 | Released | LLMBoard43.44 | ParametersN/A | Context256K | Max output8K | Open weightsNo | LicenseProprietary |
Models similar to Grok 4.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 4.3
xAI
XA
Grok 3 Mini
xAI
XA
Grok 4.1 Thinking
xAI
XA
Grok Code Fast 1
xAI
XA
Grok 4 Fast
xAI
XA
Grok 3
xAI
What is Grok 4.1?
Key information about Grok 4.1 and its available data.
1 (Non-Thinking) is an xAI language model that generates immediate responses without using thinking tokens.
Compared with previous versions, it has reduced hallucinations, improved factual accuracy for information-seeking prompts, and safety measures including refusal training, input filters, and adversarial robustness measures.
Data as of 2026-09-08.
FAQ
Common questions about Grok 4.1.
When was Grok 4.1 released?
Grok 4.1's default version was released on Nov 17, 2025.
How much does Grok 4.1 cost?
No official standard PAYG price is currently available for Grok 4.1. The lowest tracked third-party offer starts at $2 input and $10 output via 302.AI.
Who created Grok 4.1?
Grok 4.1 was created by xAI.
What is the context window for Grok 4.1?
The default version has a 256K token context window.
Is Grok 4.1 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 4.1?
1 provider offerings are linked to the default version.