About
Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not...
Related Models
Pricing
Input
$5.50
per 1M tokens
Output
$27.50
per 1M tokens
Blended
$11.00
per 1M tokens
Cheaper than 5% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$11.00
Monthly
$330.00
vs. Similar Models
MiMo-V2-Flash (Feb 2026)Q:-0.1
$0.15-99%
DeepSeek V3.2 (Reasoning)Q:+0.1
$0.34-97%
Gemini 3 Pro Preview (low)Q:-0.2
$4.50-59%
GPT-5.5 Instant (May 2026)Q:+0.2
$11.25+2%
Performance
47
tokens/sec
Faster than 13% of models
19.25
seconds
Faster than 6% of models
19.25
seconds
Faster than 26% of models
Market Median
94 tok/s
50% slower
Median TTFT
1.11s
1630% slower
Throughput/Dollar
4
tok/s per $/1M
Speed Comparison
Llama 3 Instruct 70B
47 tok/s-0%
Claude 4 Sonnet (Non-reasoning)
47 tok/s+0%
Microsoft: Phi 4 Mini Instruct
47 tok/s-0%
Context Window
256K
tokens
Larger than 58% of models
Benchmarks
MMLU-Pro
86.6%
GPQA Diamond
87.7%
HLE
23.9%
LiveCodeBench
81.9%
SciCode
45.7%
TerminalBench Hard
37.9%
MATH-500
99.0%
AIME
94.3%
AIME 2025
92.7%
IFBench
53.7%
Long Context Recall
68.0%
Tau2
74.9%
Market AverageTop Score