Inkling Small

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 the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

Speech-to-textThinkingmachines1M tokens$0.4905 / min

thinkingmachines/inkling-small

Context
1M tokens
Completion cap
262,144
Tools
Yes
JSON
Yes
Released
2026-07-30

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling-small",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Inkling Small?
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 the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation. Inkling Small runs on the Geek Hub API (OpenAI-compatible). Model id: thinkingmachines/inkling-small.
Is Inkling Small free?
No. $0.4905 per minute on Geek Hub.
What is the context length of Inkling Small?
Inkling Small has a 1M tokens context window. It supports up to 262,144 completion tokens.
When was Inkling Small released?
Inkling Small was released on 2026-07-30.

More models from Thinkingmachines