Route order log in sign up
1 pick your primary route

Thinking Machines: Inkling Small

thinkingmachines/inkling-small · agent · text+image+audio->text · 524k ctx · added 2026-07-30
$0.2728·1.1998 /M effective hit 46% 1.99B/d

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

view
openrouter/thinkingmachines/inkling-small
Thinking Machines: Inkling Small · agent · text+image+audio->text · 524k ctx
1.99B/d 46% $0.2728·1.1998 – 3mo
sticker
life 429 tok/d dp age
⚡ ¢ᵉ ♻
baseten/fp8
$0.5000·1.2000·0.1000 · $0.3167·1.2000ⁱ $0.1244·1.1995ᵉ · 94% · – – – · ✓ 244ms · 106t/s · ✕1mo ·
¢ ¢ⁱ ✓ ★
deepinfra/fp8
$0.4500·1.2000·0.1000 $0.2896·1.2000ⁱ $0.2728·1.1998ᵉ 46% – – 100% ✓ 531ms 52t/s 3mo ·
together
$0.5000·1.2000·0.1000 · $0.3167·1.2000ⁱ $0.2779·1.1998ᵉ · 56% · – – – · ✓ – · – · ✕1mo ·
vercel/thinkingmachines/inkling-small
Inkling Small · agent · text+image+pdf->text · 1M ctx
– 56% $0.1900·1.2000 – 3mo
hf/thinkingmachines/Inkling-Small
Inkling-Small · agent · text+image->text · 524k ctx
– $0.4500·1.2000 – 3mo
compare all models →