About
Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
Related Models
Pricing
Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Blended
$3.00
per 1M tokens
Cheaper than 22% of models. Median price is $0.66/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.00
Monthly
$90.00
vs. Similar Models
GPT-5.6 Sol (medium)Q:-0.2
$11.25+275%
Anthropic: Claude Opus 4.7Q:-0.3
$10.00+233%
Anthropic: Claude Sonnet 5Q:-0.4
$4.00+33%
GPT-5.5 (high)Q:-0.7
$11.25+275%
Performance
110
tokens/sec
Faster than 57% of models
13.54
seconds
Faster than 11% of models
13.54
seconds
Faster than 34% of models
Market Median
99 tok/s
11% faster
Median TTFT
1.11s
1123% slower
Throughput/Dollar
37
tok/s per $/1M
Speed Comparison
GLM-5.2 (Non-reasoning)
110 tok/s-0%
MiMo-V2-Flash (Non-reasoning)
110 tok/s+0%
Qwen3 Omni 30B A3B Instruct
109 tok/s-0%
Context Window
500K
tokens
Larger than 79% of models
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
93.1%
HLE
40.3%
LiveCodeBenchNot evaluated
SciCode
54.1%
TerminalBench HardNot evaluated
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context Recall
67.7%
Tau2Not evaluated
Market AverageTop Score