Pass IndexThe State of AISign in

Inkling Small

Inkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe, to Inkling that achieves strong performance with even lower cost and latency.

text + image + file → text · made by Thinking Machines Lab

$0.3$1.2per Mtok in / out
Thinking Machines Lab · 8 sellers

Free

Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.

Sold by 20 ways

SellerLaneRate
Thinking Machines Lab apistandard$0.3per Mtok in$1.2per Mtok out$0.06per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
Thinking Machines Lab apitraining$0.58per Mtok in$1.44per Mtok out$0.12per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
Thinking Machines Lab apitraining-256k$1.16per Mtok in$2.89per Mtok out$0.23per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
OpenRouter 5 ways$0.45per Mtok in$1.2per Mtok out$0.1per Mtok cached
OpenRouter aggregatorfree$0per Mtok in$0per Mtok outopenrouter.ai · read 2026-09-16
OpenRouter aggregatorstandard$0.45per Mtok in$1.2per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-24
OpenRouter aggregatorbaseten/fp8$0.5per Mtok in$1.2per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatorbatch$0.5per Mtok in$1.2per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-29
OpenRouter aggregatortogether$0.5per Mtok in$1.2per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25
Nous Research 2 ways$0.45per Mtok in$1.2per Mtok out$0.1per Mtok cached
Nous Research aggregatornot on the seller's list todayresold$0.36per Mtok in$0.96per Mtok out$0.08per Mtok cachedinference-api.nousresearch.com · read 2026-08-25
Nous Research aggregatorstandard$0.45per Mtok in$1.2per Mtok out$0.1per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
Nous Research aggregatorbatch$0.5per Mtok in$1.2per Mtok out$0.1per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
DeepInfra aggregatorstandard$0.45per Mtok in$1.2per Mtok outapi.deepinfra.com · read 2026-08-25
ElectronHub 0 ways$0.45per Mtok in$1.2per Mtok out
ElectronHub aggregatornot on the seller's list todaystandard$0.45per Mtok in$1.2per Mtok outapi.electronhub.ai · read 2026-09-05
Hugging Face Inference Providers 4 ways$0.5per Mtok in$1.2per Mtok out
Hugging Face Inference Providers aggregatordeepinfra$0.45per Mtok in$1.2per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatorstandard$0.5per Mtok in$1.2per Mtok outmodels.dev · read 2026-09-16
Hugging Face Inference Providers aggregatorbaseten$0.5per Mtok in$1.2per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatortogether$0.5per Mtok in$1.2per Mtok outrouter.huggingface.co · read 2026-08-25
Baseten aggregatorstandard$0.5per Mtok in$1.2per Mtok out$0.5per Mtok cachedbaseten.co · read 2026-08-25
Together AI aggregatorstandard$0.5per Mtok in$1.2per Mtok out$0.1per Mtok cacheddocs.together.ai · read 2026-08-24
Vercel AI Gateway aggregatorstandard$0.5per Mtok in$1.2per Mtok out$0.1per Mtok cachedai-gateway.vercel.sh · read 2026-08-25

Measured 21 standings

PlaceBoardMetricScore
42ndof 106Frontiermath tiers 1 3 v2 — Epoch AImean_score (xhigh)46.316
44thof 62Frontiermath tier 4 v2 — Epoch AImean_score (xhigh)17.073
51stof 313GPQA Diamondmean_score (xhigh)88.51
56thof 64Proofbench — Epoch AIAccuracy6
62ndof 143Artificial Analysis · Agentic IndexIndex25
62ndof 290OTIS Mock AIME 2024-2025mean_score (xhigh)90
68thof 80Simpleqa verified — Epoch AImean_score (xhigh)19.1
70thof 168Scicode — Epoch AIScore48.727
71stof 177Critpt — Epoch AIAccuracy8.286
72ndof 121Webdev arena — Epoch AIArena Score1401.56
74thof 216ARC-AGI-2 (Public Eval)Score (%) (xhigh)39.31
75thof 205ARC-AGI-1 (Public Eval)Score (%) (xhigh)89.38
78thof 184Artificial Analysis · Coding IndexIndex52.9
81stof 230ARC-AGI-1 (Semi-Private)Score (%) (xhigh)84
82ndof 232ARC-AGI-2 (Semi-Private)Score (%) (xhigh)40.14
87thof 302Artificial Analysis · Intelligence IndexArtificial Analysis Intelligence Index26
90thof 227Arc agi 2 — Epoch AIScore (xhigh)40.139
92ndof 244Arc agi — Epoch AIScore (xhigh)84
96thof 222Chess puzzles — Epoch AImean_score (xhigh)18
117thof 127Mystery game puzzles — Epoch AImean_score (xhigh)6
206thof 656Epoch capabilities index — Epoch AIECI Score (xhigh)150.16

About

Inkling Small — a text model from Thinking Machines Lab, sold by 8 companies from $0.3 in and $1.2 out per million tokens, placed 51st of 313 on GPQA Diamond.

It takes text, images and files and returns text, with a context window of 1,000,000 tokens. It was published in July 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Eight companies sell it. The cheapest is $0.3 in and $1.2 out per million tokens at Thinking Machines Lab. Beside the standard rate there are separately routed, batch and regional lanes. It has been measured on 21 boards, and stands best at 51st of 313 on GPQA Diamond.

Every current figure

Maker
Thinking Machines Lab
Register
model
Takes
text + image + file
Returns
text
Context
1,000,000 tokens
Published
July 2026
Parameters
266 billion
Licence
not read
Sellers
8
Price
$0.3 in and $1.2 out per million tokens — Thinking Machines Lab
Boards
21
Best place
51st of 313 — GPQA Diamond

Known as 3 names

thinkingmachines/inkling-smallthinkingmachines/Inkling-Small:peft:262144thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4