Inkling Small (batch)
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.
thinkingmachines/inkling-small:batch
- Context
- 524k tokens
- Completion cap
- 471,859
- Tools
- Yes
- JSON
- No
- 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:batch",
"messages": [{"role": "user", "content": "Hola"}]
}'Get an API keyFrequently asked questions
- What is Inkling Small (batch)?
- 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 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: thinkingmachines/inkling-small:batch.
- Is Inkling Small (batch) free?
- No. $0.545 per minute on Geek Hub.
- What is the context length of Inkling Small (batch)?
- Inkling Small (batch) has a 524k tokens context window. It supports up to 471,859 completion tokens.
- When was Inkling Small (batch) released?
- Inkling Small (batch) was released on 2026-07-30.
More models from Thinking Machines
InklingInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning
Inkling (batch)Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning
Inkling (free)Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning
Inkling SmallInkling 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
Inkling Small (free)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