prices synced 2026-09-15
T

Inkling Small

Thinking Machines · Multimodal · Released Jul 2026

Compare

Open-weight multimodal mixture-of-experts model with 12B active parameters from 276B total and 524K token context.

Strengths
Efficient inference from a sparse parameter architecture while maintaining multimodal capabilities across long contexts.
Best for
Applications where reduced computational requirements and faster latency are prioritized over the scale of the full Inkling model.
Limitations
Smaller active parameter count compared to Inkling means reduced reasoning depth and knowledge capacity for complex tasks.

Input / 1M

$0.45

Output / 1M

$1.20

Cached input / 1M

$0.1

Context window

524K

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $1.44 to $1.20; Input went from $0.58 to $0.45 between Jul 2026 and Aug 2026.$0$0.5$1.00$1.50Output on 31 Jul 2026: $1.44Output on 1 Aug 2026: $1.20Output on 7 Aug 2026: $1.20Out $1.20Input on 31 Jul 2026: $0.58Input on 1 Aug 2026: $0.5Input on 7 Aug 2026: $0.45In $0.45Jul 2026Aug 2026

Price change

30d
in out
90d
in decreased 22.4% out decreased 16.7%
1y
in decreased 22.4% out decreased 16.7%
Since launch
in decreased 22.4% out decreased 16.7%

Snapshots

Effective Input Output Cached in Note Source
7 Aug 2026 $0.45 $1.20 $0.1 Imported from OpenRouter openrouter.ai
1 Aug 2026 $0.5 $1.20 $0.1 Imported from OpenRouter openrouter.ai
31 Jul 2026 $0.58 $1.44 $0.116 Imported from OpenRouter openrouter.ai

More from Thinking Machines

Report a problem