Thinking Machines Inkling

thinkingmachines/inkling

Run Thinking Machines Inkling in a hosted Python Task with extended thinking and file inputs.

Thinking Machines Lab's Inkling via OpenRouter. An open-weight mixture-of-experts model (975B total, 41B active parameters) for coding and tool use. Accepts image and audio input with a 524K token context window.

What Thinking Machines Inkling supports in qbash

Extended thinkingReasons through a problem before it replies.
Reasoning effort5 levels, from minimal to max.
Image inputReads WEBP, PNG, JPEG and GIF images.
Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more files.
Prompt cachingRepeated input is billed at the cached rate.

What is qbash?

qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like Thinking Machines Inkling only at the ones that need judgment, with integrations, memory and files available in the same script.

A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.

How Tasks work

Specifications

Context window: 524Ktokens
Max output: 131,072tokens
Temperature: 0 to 1default 1

Use Thinking Machines Inkling in a Python Task

qbash.ai.raw calls Thinking Machines Inkling from a Task and returns its reply as a string.

main.py
notes = qbash.inputs.get("notes")

summary = qbash.ai.raw(
    f"Summarize these meeting notes in five bullets:\n\n{notes}",
    model="thinkingmachines/inkling",
    system="You are a concise analyst.",
)

qbash.output({"summary": summary})

Model calls in Tasks

Reasoning effort with Thinking Machines Inkling

Set Effort to minimal, low, medium, high and max in the prompt's Settings. Higher effort spends more tokens on reasoning before the reply.

Turn on Thinking in the same Settings popover to have Thinking Machines Inkling reason through a problem before it replies.