Passer au contenu principal

Grok 4.1 Fast (Reasoning)

SpaceXAIGrokProprietary

Description

Grok 4.1 Thinking (code name: quasarflux) is the reasoning variant of Grok 4.1, bringing significant improvements to the real-world usability of Grok. The model is exceptionally capable in creative, emotional, and collaborative interactions. It is more perceptive to nuanced intent, compelling to speak with, and coherent in personality, while fully retaining the razor-sharp intelligence and reliability of its predecessors. Grok 4.1 Thinking uses thinking tokens for deeper reasoning, achieving state-of-the-art performance on blind human preference evaluations. The model features reduced hallucinations compared to previous versions, with significant improvements in factual accuracy for information-seeking prompts. To achieve this, xAI used large scale reinforcement learning infrastructure to optimize style, personality, helpfulness, and alignment, developing new methods that use frontier agentic reasoning models as reward models to autonomously evaluate and iterate on responses at scale. Grok 4.1 Thinking includes comprehensive safety mitigations including refusal training, input filters for restricted knowledge, and adversarial robustness measures. The model demonstrates strong refusal rates on harmful queries (7% answer rate on chat refusals, 14% on agentic refusals) and improved honesty training to reduce deception.

Date de sortie
2025-11-19
Paramètres
—
Longueur du contexte
—
Modalités
image, text

Radar de capacités

50
general
40
coding
21
reasoning
26
scienceest.
40
agents
80
multimodal

Science est estimé à partir des scores scientifiques de LLM Stats ou du raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.

Classements

Aucune donnée de classement disponible

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Biology

BioLP-Bench37.0%Aut.

Chat

EQ-Bench1586.00 / 2000Aut.
LMArena Text Leaderboard1483.00 / 2000Aut.

Creativity

Creative Writing v386.1%Aut.

Safety

WMDP84.0%Aut.
ProtocolQA79.0%Aut.
Virology Capabilities Test61.0%Aut.
MASK51.0%Aut.
CloningScenarios46.0%Aut.
CyBench39.0%Aut.
FigQA34.0%Aut.

Indices d'évaluation AA

(Artificial Analysis)

Aucune donnée d'évaluation AA disponible

Scores par catégorie LLM Stats

(LLM Stats (zeroeval))
Creativity
90
Writing
90
General
50
Safety
40
Agents
40
Code
40
Healthcare
30
Vision
30

Tarification

Prix d'entrée$0.2 / 1M tokens
Prix de sortie$0.5 / 1M tokens
Prix mixte (3:1)$0.275 / 1M tokens

Vitesse

Aucune donnée de vitesse disponible

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

8 fournisseurs

Moins cher: Jiekou.AIPlus cher: Azure
FournisseurEntréeSortie
1Jiekou.AIMoins cher
$0.19
$0.475
2SpaceXAIPRINCIPAL
$0.2
$0.5
3302.AI
$0.2
$0.5
4Helicone
$0.2
$0.5
5FrogBot
$0.2
$0.5
6Azure Cognitive Services
$0.2
$0.5
7DevPass (LLM Gateway)
$0.2
$0.5
8Azure
$0.2
$0.5

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes