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, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

Speech-to-textThinkingmachines524k tokens$1.0901 / min

thinkingmachines/inkling:batch

Context
524k tokens
Completion cap
—
Tools
Yes
JSON
No
Released
2026-07-17

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:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text. Inkling (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: thinkingmachines/inkling:batch.
Is Inkling (batch) free?
No. $1.0901 per minute on Geek Hub.
What is the context length of Inkling (batch)?
Inkling (batch) has a 524k tokens context window.
When was Inkling (batch) released?
Inkling (batch) was released on 2026-07-17.

More models from Thinkingmachines