Thinking Machines: 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.

Context
524K
Max output
262K
Input price
$0.45/1M tokens
Output price
$1.2/1M tokens

Capabilities

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

Details

Model IDthinkingmachines/inkling-small
Provider OpenRouter
Creator thinkingmachines
Family—
License—
Status—
Type—
Input modalitiestext, image, audio
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window524K tokens
Max input—
Max output262K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.45
Output
$1.2
Cache write
—
Cache read
$0.1
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/thinkingmachines/inkling-small

Thinking Machines: Inkling Small

thinkingmachines/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.

Changes · 5 entries
thinkingmachines/inkling-smallcreateca7a400Nov 2, 2026, 03:02 AM
thinkingmachines/inkling-smallupdate9cb03f8Sep 26, 2026, 06:38 AM
context_window1048576→524288
thinkingmachines/inkling-smallupdatee3d7dedAug 31, 2026, 04:13 AM
context_window524288→1048576
thinkingmachines/inkling-smallupdate3cddff5Aug 13, 2026, 02:54 AM
pricinginput$0.5→$0.45
max_output_tokens262144
thinkingmachines/inkling-smallcreate86db01cAug 2, 2026, 08:20 AM