Private AI
Compatibility alias that routes to the newest Grok model. Currently routes to Grok 4.5. Content policy rejections can still be charged: xAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Added May 3, 2026
Context Window
500.0K
Max Output
500.0K
Input Price (Auto)
$2.10/1M
Output Price (Auto)
$6.30/1M
Cache Read (Auto)
$0.53/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
53.8
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
72.4
Agentic Index
45.7
GPQA Diamond
Graduate-level scientific reasoning
93.1%
Better than 98% of models compared
HLE
Humanity's Last Exam
40.3%
Better than 96% of models compared
AA-LCR
Long context reasoning evaluation
67.7%
Better than 87% of models compared
GDPval-AA
Economically valuable tasks
51.4%
CritPt
Research-level physics reasoning
15.4%
SciCode
Python programming for scientific computing
54.1%
Better than 97% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
52.0%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
53.5%
Last updated Aug 4, 2026
Artificial Analysis