Thinking Machines: Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.

Context
524K
Max output
472K
Input price
$1/1M tokens
Output price
$4.05/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode

Details

Model IDthinkingmachines/inkling
Provider OpenRouter
Creator thinkingmachines
Family—
License—
Status—
Type—
Input modalitiestext, image, audio
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window524K tokens
Max input—
Max output472K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$1
Output
$4.05
Cache write
—
Cache read
$0.17
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/thinkingmachines/inkling