What are the key specifications of Inkling?

Inkling is a Mixture-of-Experts Transformer with 975 billion total parameters and 41 billion active parameters, pretrained on 45 trillion tokens of text, image, audio, and video data. It supports a maximum context window of 1 million tokens and allows users to adjust the computational effort spent on reasoning to balance cost, latency, and performance.

How can developers use Inkling?

Developers can customize Inkling via Thinking Machines Lab's fine-tuning platform Tinker, starting immediately on the announcement date. The platform is offered at a 50% discount for a limited period, and an Inkling Playground has been added to the Tinker console to allow developers to interact with the model directly.

What is the lightweight version of Inkling?

Inkling-Small is a preview version with 276 billion total parameters and 12 billion active parameters. It demonstrates performance comparable to the full Inkling model on many benchmarks, with weights to be released after testing is complete.

Open-Source AIITmedia AI＋Jul 16, 2026Jul 16, 2026, 10:00 JST2 min read

Thinking Machines、初のAIモデル「Inkling」を公開

Send on LINE

Key takeaway

Thinking Machines Lab has released Inkling, its first AI model, as an open-source multimodal foundation model supporting text, image, audio, and video inputs. With 975 billion total parameters and 41 billion active parameters, Inkling was pretrained on 45 trillion tokens and supports a context window of up to 1 million tokens.
The company positions Inkling as a customization-friendly base model designed for fine-tuning, allowing users to adapt it to specific needs rather than serving as the strongest available model off-the-shelf.
Developers can customize Inkling immediately via the Tinker platform at a 50% discount during a limited period.

3 Key Points

What happened
Thinking Machines Lab（OpenAI元CTOのミラ・ムラティ氏が設立）が7月15日、初のAIモデル「Inkling」を発表した。テキスト、画像、音声、動画に対応するマルチモーダルモデルで、Apache 2.0ライセンスの下、全ウェイトをHugging Faceで公開している。総パラメータ数9750億、アクティブパラメータ数410億のMoE型Transformerで、最大100万トークンのコンテキストウィンドウをサポートする。
Why it matters
Inklingはカスタマイズに適したオープンウェイト基盤として位置付けられており、ユーザーが「自分のものにできる」ことを重視している。推論に費やす思考の労力を調整できる仕組みにより、コストや遅延と性能のバランスを制御でき、ファインチューニングがしやすいため、特定の用途に合わせて調整したいユーザーにとって柔軟な選択肢となる可能性がある。
What to watch
開発者はファインチューニングプラットフォーム「Tinker」で同日からInklingをカスタマイズでき、期間限定で50％割引価格で提供される。軽量版「Inkling-Small」（総パラメータ数2760億、アクティブパラメータ数120億）のプレビューも公開され、テスト完了後にウェイトが公開予定。推論プロバイダーのTogetherAIやFireworksとも提携し、ファインチューニング済みモデルの展開に向けて進展している。

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Get news like this every morning — free

Context & Analysis

Thinking Machines Lab, founded by Mira Murati following her tenure as OpenAI's CTO, has entered the AI model space with a philosophy distinct from the pursuit of raw performance. Rather than claiming to offer the strongest available model, the company explicitly positions Inkling as a base designed for customization and adaptation. This strategy reflects a stated mission to "build AI that extends human will and judgment," emphasizing user agency over centralized capability.

The technical design of Inkling supports this positioning. Its Mixture-of-Experts architecture with tunable computational effort allows users to trade off speed, cost, and quality for their specific use cases—a feature particularly valuable for organizations that cannot deploy the largest models but need flexibility. The 45 trillion token pretraining corpus spanning text, image, audio, and video positions Inkling as a true multimodal foundation, though the company does not claim superiority on specific benchmarks.

The commercial model—open-source weights under Apache 2.0 license, coupled with a paid fine-tuning platform (Tinker) and partnerships with inference providers TogetherAI and Fireworks—suggests Thinking Machines intends to capture value through customization services and deployment rather than access restrictions. The immediate availability of a lightweight variant (Inkling-Small) and self-fine-tuning demos indicate the company is lowering barriers to adaptation, potentially making Inkling appealing to developers and organizations seeking control over their AI systems.

FAQ

What are the key specifications of Inkling?: Inkling is a Mixture-of-Experts Transformer with 975 billion total parameters and 41 billion active parameters, pretrained on 45 trillion tokens of text, image, audio, and video data. It supports a maximum context window of 1 million tokens and allows users to adjust the computational effort spent on reasoning to balance cost, latency, and performance.
How can developers use Inkling?: Developers can customize Inkling via Thinking Machines Lab's fine-tuning platform Tinker, starting immediately on the announcement date. The platform is offered at a 50% discount for a limited period, and an Inkling Playground has been added to the Tinker console to allow developers to interact with the model directly.
What is the lightweight version of Inkling?: Inkling-Small is a preview version with 276 billion total parameters and 12 billion active parameters. It demonstrates performance comparable to the full Inkling model on many benchmarks, with weights to be released after testing is complete.

ITmedia AI＋Read Original Article

Send on LINE

Get the latest Open-Source AI news every morning

For example, today's edition would include:

DataAgent launches with $10M to auto-fix Kubernetes faultsSiliconANGLE AI · 4h ago
Z.ai runs GLM on 100,000 Chinese AI chipsDIGITIMES Asia · 7h ago
Broadcom Unveils VMware AI Factory for Faster Private AITop Companies AI · 16h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Subscribe free →

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →