Inkling 2 Small (free)
Thinking Machines Lab🇺🇸
thinkingmachines/inkling-2-small:freeInkling 2 Small is a multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.
Cost rate
Free
Context
1M
Released
Nov 9, 2026
Input
TextImage
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Business, Management, & Finance
#119 · top 29%
Software & IT Services
#122 · top 29%
Life, Physical, & Social Science
#156 · top 37%
Writing, Literature, & Language
#162 · top 39%
Performance
Median latency and throughput measured across recent requests.
Throughput115 tok/s
Latency2.26s