Private AI
An open-weight, 117B-parameter Mixture-of-Experts (MoE) language model designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Added Feb 3, 2026
Model weightsContext Window
128.0K
Max Output
16.4K
Input Price (Auto)
$0.032/1M
Output Price (Auto)
$0.18/1M
Cache Read (Auto)
$0.032/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.8
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
30.4
GPQA Diamond
Graduate-level scientific reasoning
78.2%
Better than 68% of models compared
HLE
Humanity's Last Exam
18.5%
Better than 77% of models compared
IFBench
Instruction-following benchmark
69.0%
Better than 83% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
65.8%
Better than 60% of models compared
AA-LCR
Long context reasoning evaluation
50.7%
Better than 57% of models compared
SciCode
Python programming for scientific computing
38.9%
Better than 68% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
23.5%
AIME 2025
American Invitational Mathematics Examination 2025
93.4%
Better than 94% of models compared
MMLU-Pro
Professional and academic subject knowledge
80.8%
Better than 71% of models compared
Last updated Aug 4, 2026
Artificial AnalysisBetter than 63% of models compared
LiveCodeBench
Contamination-free coding benchmark
87.8%
Better than 98% of models compared
