Inkling: Our open-weights model

Mira Murati’s Thinking Machines Lab has released Inkling, an open-weights model with 975 billion total parameters and 41 billion active. The Apache-2.0…

By Vane July 16, 2026 3 min read
Inkling: Our open-weights model

Mira Murati’s Thinking Machines Lab has released Inkling, an open-weights model with 975 billion total parameters and 41 billion active. The Apache-2.0 licensed system is multimodal, trained on 45 trillion tokens of text, images, audio, and video.

What is coming next

They are also developing Inkling-Small, a 276 billion parameter model with 12 billion active. That version is currently being tested. The weights will be released once the work is finished.

The model card is notably shorter than those from other US AI labs. It links to training data documentation that contains almost nothing of interest. The text states the lab uses public domain content and material subject to intellectual property protection. It notes services were developed using publicly available content from the open internet and accessible data repositories. Certain datasets came from third parties.

Thinking Machines admits Inkling is not the strongest overall model available today, open or closed. The description says a combination of qualities makes it a good open-weights base for customization. These include multimodal capabilities, efficient thinking, and availability on Tinker for fine-tuning.

Why this matters for builders

There is a lot to like about this release. It is Apache-2.0 licensed and looks competitive with the open weight models coming out of China. It is good to see the US open weights ecosystem gain a new viable contender to join NVIDIA Nemotron and Gemma 4.

I generated an SVG of a pelican riding a bicycle using this command against the Thinking Machines API:

curl "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1/chat/completions" \
  -H "Authorization: Bearer $TINKER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/Inkling",
    "messages": [
      {"role": "user", "content": "Generate an SVG of a pelican riding a bicycle"}
    ],
    "stream": false
  }'

Response here

See image description below

Since it is a multi-modal model I had it describe its own image after I rendered it to a JPEG. I sent this JSON:

{
  "model": "thinkingmachines/Inkling",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,$BASE_64_JPEG"}},
      {"type": "text", "text": "Describe this image in detail"},
    ],
  }],
  "stream": false
}

Full response here. It thought it had drawn a stork or seagull:

This is a cheerful, flat-vector cartoon illustration featuring a white bird riding a bicycle across a green landscape.

The Bird: The central figure is a stylized white bird—resembling a stork or seagull—with a plump, rounded body. It has a long, prominent orange beak that is slightly open, revealing a black line for the mouth. Its eye is small and black with a tiny white highlight. The bird has black wing and tail feathers with white edges, and thin orange legs ending in black feet that rest on the bicycle’s orange pedals.

The Bicycle: The bike has a simple black frame with two large wheels featuring black tires, gray inner rims, and black spokes arranged in a cross pattern. The handlebars are black, and there are bright orange pedals attached to a black crank. A white seat is visible behind the bird’s body.

The Setting: The scene is set against a clear, light blue sky. There are two fluffy white clouds—one on the left side and a smaller one near the bird’s head on the right. A bright, solid yellow sun shines in the upper right corner. At the bottom, there are rolling green hills with a smooth, curved top edge where the bicycle rests.

The overall style is playful, simple, and colorful, with clean lines and a bright, sunny atmosphere.

Via Hacker News

Scroll to Top