someaistuff.
thinkingmachinesListed Jul 17, 2026

Thinking Machines: Inkling (free)

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,...

Compare
Context window1M
Max output262.1K
Provider endpoints2
Benchmark results0
Image inputAudio inputTool callingReasoningOpen weights
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

2 quotes

OpenRouter

Catalog quote
Input
$0.00
Output
$0.00
USD / 1M tokens
1M context262.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDthinkingmachines/inkling:free

Thinking Machines

via OpenRouter

thinkingmachines/nvfp4 · quantization=nvfp4

Input
$0.00
Output
$0.00
USD / 1M tokens
1M context262.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDthinkingmachines/inkling:free::thinkingmachines/nvfp4

Offers for this model

1 offer

OpenRouter · Free access

21 OpenRouter zero-token-price variants

Free variants have request limits.

Checked Source ↗

View offer ↗

Model specifications

Developer
thinkingmachines
Modality
Language
Context
1,048,576 tokens
Maximum output
262,144 tokens
Weights
Open weights
Provider listed
Jul 17, 2026
First discovered
Oct 16, 2026

Exact identities

  • openrouterthinkingmachines/inkling:free

Sources

OpenRouter ↗

Updated Oct 17, 2026

More from thinkingmachines

View all ↗
thinkingmachinesListed Jul 30

Thinking Machines: Inkling Small (free)

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...

1M contextImage inputAudio inputNo reported score
No reported score
$0.00in$0.00out/ 1M tokens · USDThinking Machines · via OpenRouter · 2 endpointsthinkingmachines/nvfp4 · quantization=nvfp4
+Compare
thinkingmachinesListed Jul 27

Inkling-Small

Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable…

524.3K contextImage inputAudio inputNo reported score
No reported score
$0.45in$1.20out/ 1M tokens · USDdeepinfra · via Hugging Face · 4 endpoints
+Compare