Input Price$0.04/1M tokens
Output Price$0.17/1M tokens
Intelligence18.2
Coding9.8
Specifications
Technical details and pricing.
Providersarvam
Context WindowN/A
Release DateMar 6, 2026
ModalitiesText
Benchmarks
7 benchmark scores from Artificial Analysis.
GPQA73.8%
HLE10.1%
SciCode26.4%
LCR0.0%
IFBench34.4%
Tau246.8%
TerminalBench Hard1.5%
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Frequently Asked Questions
What is 105B (high) good for?
105B (high) currently has benchmark and pricing data on this page. Runtime metadata will appear later when the model catalog entry becomes available.
How much does 105B (high) cost?
Pricing is based on usage. Current rates are $0.04/1M tokens for input and $0.17/1M tokens for output.
Is 105B (high) available in LLMBase Chat yet?
Not yet on this page. We will add chat and inference actions automatically once an exact catalog entry exists for 105B (high).
Does 105B (high) support images or audio?
105B (high) focuses on text-based tasks.
Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.