Thinking Machines

Inkling Small (batch)

thinkingmachines/inkling-small:batch

Specification

Published by the vendor; the platform bills at the target's declared price.

Inkling Small (batch)

reasoning open weights tools

Thinking Machines thinkingmachines/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...

Input $/1M: $0.50
Output $/1M: $1.20
Context: 524K
Max output: 472K
Released: Jul 30, 2026
Modalities: textimageaudio

Intelligence index-

Coding index53

Agentic index25

Cached input reads $0.10 per 1M · weights on Hugging Face as thinkingmachines/Inkling-Small

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Inkling Small (batch)
targets:
  - id: inkling-small-batch
    kind: llm
    name: Inkling Small (batch)
    metadata:
      model: thinkingmachines/inkling-small:batch          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 524288
    cost:
      usd_per_1k_tokens: 0.000850

Price among Thinking Machines models

Input list price per million tokens; Inkling Small (batch) is the 4th cheapest of 6 listed.

1
Inkling Small (free)
free
2
Inkling (free)
free
3
Inkling Small
$0.45
4
Inkling Small (batch)
$0.50
5
Inkling
$1.00
6
Inkling (batch)
$1.00

More from Thinking Machines

Other models by the same vendor in the catalogue.