Inkling (batch)
Thinking Machines Lab馃嚭馃嚫
thinkingmachines/inkling:batchThis is the batch-processing variant of Thinking Machines Lab's Inkling model, a 975B-parameter open-weights multimodal MoE model that reasons over text, images, and audio. It offers the same capabilities as standard Inkling at lower cost for asynchronous, non-latency-sensitive workloads.
Cost rate
0.8x
Context
524K
Released
Jul 17, 2026
Input
TextImageAudio
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Mathematical
#49 路 top 13%
Life, Physical, & Social Science
#74 路 top 19%
Software & IT Services
#77 路 top 20%
Business, Management, & Finance
#79 路 top 20%