Inkling
Thinking Machines Lab馃嚭馃嚫
thinkingmachines/inklingInkling is Thinking Machines Lab's first flagship model, a 975B-parameter (41B active) open-weights mixture-of-experts model that reasons natively over text, images, and audio with up to a 1M-token context window. It is designed as a general-purpose frontier model for multimodal reasoning and agentic tasks, released under Apache 2.0.
Cost rate
0.8x
Context
1M
Released
Jul 17, 2026
Input
TextImageAudio
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Mathematical
#58 路 top 15%
Software & IT Services
#78 路 top 19%
Business, Management, & Finance
#83 路 top 21%
Life, Physical, & Social Science
#87 路 top 22%
Performance
Median latency and throughput measured across recent requests.
Throughput91 tok/s
Latency