Inference Index
←All models
Directory · Models · xAI
Grok

Grok 4

xAI’s latest. Real-time X search integration, strong on current events and meme-literate tasks.

Input / 1M
$5.00
Output / 1M
$15.00
Context
256K
Released
Mar 1, 2026

Benchmark profile

MMLU-ProHumanEvalMATHIFEvalARC-AGIGSM8K
Profile
MMLU-Pro86.2%
HumanEval88.4%
MATH86.5%
IFEval85.0%
ARC-AGI86.5%
GSM8K86.5%

Scores

MMLU-Proknowledge
86.2%
HumanEvalcoding
88.4%
LMSYS Chatbot Arenaarena
1358ELO
MATHmath
86.5%
IFEvalinstruction
85.0%
ARC-AGIreasoning
86.5%
GSM8Kmath
86.5%
TruthfulQAsafety
85.0%

Editorial

Strengths
  • +Live web/X access
  • +Personality
  • +Fast inference on Colossus
Trade-offs
  • −Smaller ecosystem of integrations

Price history (last 90 days)

Input / 1M
Output / 1M
04-1804-2705-0605-1605-2506-0306-13$0.00$5.00$10.00$15.00

What this costs to use

All task cards →
Compare across every model →

Recommended alternatives

Cheaper
Claude Sonnet 4.6
Anthropic
$3.00/M · $15.00/M−10%
Stronger
GPT-5 Turbo
OpenAI
$6.00/M · $24.00/M+50%
Direct competitor
Qwen 3 Max
Qwen
$1.60/M · $6.40/M−60%

Where to buy

All providers →
Input pricing · $/1M tokens · sorted cheapest first