Thinking Machines

Inkling Small

Jul 30, 2026ReasoningOpen weightsModels.dev

Compare

Intelligence

12.9

#357 of 760Rank 357 of 760 measured models

Coding

52.9

#109 of 299Rank 109 of 299 measured models

Output speed

208 t/s

#44 of 419Rank 44 of 419 measured models

Price/1M

$0.525

#307 of 713Rank 307 of 713 measured models

Context window

1M

#88 of 1279Rank 88 of 1279 measured models

Cost per task

$0.203

#74 of 212Rank 74 of 212 measured models

Inkling Small scores 12.9 on the Artificial Analysis Intelligence Index, ranking 357th of 760 measured models. The closest models on this index are GPT-5 nano (13.0), Nemotron 3.5 Lightning (12.9), and GLM-4.5 (Reasoning) (12.8). At $0.525 per million tokens (3:1 input/output blended price), it is more expensive than GPT-5 nano ($0.138) and Nemotron 3.5 Lightning ($0.095). With an output speed of 208 t/s, it is faster than GPT-5 nano (138 t/s), slower than Nemotron 3.5 Lightning (296 t/s).