About
Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model...
Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.50
per 1M tokens
Blended
$0.28
per 1M tokens
Cheaper than 63% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.28
Monthly
$8.25
vs. Similar Models
Z.ai: GLM 4.5 AirQ:0.0
$0.31+13%
GPT-5.4 mini (Non-Reasoning)Q:+0.1
$1.69+514%
Nova 2.0 Omni (low)Q:+0.1
$0.85+209%
OpenAI: GPT-4.1 MiniQ:-0.2
$0.70+155%
Performance
98
tokens/sec
Faster than 53% of models
0.41
seconds
Faster than 95% of models
0.41
seconds
Faster than 97% of models
Market Median
94 tok/s
4% faster
Median TTFT
1.11s
64% faster
Throughput/Dollar
356
tok/s per $/1M
Speed Comparison
Olmo 3.1 32B Think
98 tok/s-0%
GPT-5 (medium)
97 tok/s-1%
Grok 4.1 Fast (Reasoning)
97 tok/s-1%
Context Window
2.0M
tokens
Larger than 98% of models
Max Output
30K
tokens
2% of context
Benchmarks
MMLU-Pro
73.0%
GPQA Diamond
60.6%
HLE
5.0%
LiveCodeBench
40.1%
SciCode
32.9%
TerminalBench Hard
12.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
41.3%
IFBench
37.7%
Long Context Recall
20.0%
Tau2
63.7%
Market AverageTop Score