RentGPU RentGPU
寻找 GPU →
by Thinkingmachines

Thinking Machines: Inkling Small.

multimodal closed 524K ctx
Cheapest input
$0.5/M
on Together AI
Cheapest output
$1.2/M
on Together AI
Hosted equiv.
~$0.43/hr
@ 100 tok/s on Together AI

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...

Hosted API only

No self-host path — closed weights.

Thinking Machines: Inkling Small's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Together AI hosted inference $0.5 $1.2 Launch ↗
DeepInfra hosted inference $0.5 $1.2 Launch ↗
OpenRouter api aggregator $0.5 $1.2 Launch ↗
FAQ

Frequently asked.

How do I run Thinking Machines: Inkling Small?
Thinking Machines: Inkling Small is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Thinking Machines: Inkling Small?
Thinking Machines: Inkling Small is available via Together AI, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Thinking Machines: Inkling Small?
API pricing starts at $0.5/M input tokens and $1.2/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Thinking Machines: Inkling Small open-source or proprietary?
Thinking Machines: Inkling Small is a proprietary model from Thinkingmachines. Access is API-only — there are no public weights to download.