July 16, 2026 — The mission of Thinking Machines Lab is to build AI that extends human will and judgment. The company has developed a platform that lets anyone customize models, previewed an AI system built for interactive collaboration, and published novel research. Thinking Machines is advancing its mission by releasing a model trained from scratch with the full weights available, so that people can make it their own.
The model, called Inkling, is a Mixture-of-Experts transformer with 975B total parameters, 41B active. It supports a context window of up to 1M tokens. It was pretrained on 45 trillion tokens of text, images, audio and video. It is the first in a family of models of different sizes: alongside it Thinking Machines Lab is sharing a preview of Inkling-Small, a lighter-weight model with 12B active parameters, trained with a similar recipe, that achieves strong performance with even lower cost and latency.
Inkling reasons natively over text, images, and audio, and balances cost with performance through efficient and controllable thinking effort. Thinking Machines Lab trained it to be a broad, balanced foundation model: strong across many domains, flexible enough to adapt. Inkling is not the strongest overall model available today, open or closed. Instead, a combination of qualities makes it a good open-weights base for customization: multimodal capabilities, efficient thinking, and availability on Tinker for fine-tuning. Inkling is just the start: it’s first release in a model family Thinking Machines Lab will continue to build on.
Thinking Machines Lab wants to make customization accessible for more use cases, so Inkling is available for fine-tuning on Tinker today. Picking the right base model to fine-tune is a qualitative judgment that combines measurable benchmarks with the unique feel of a model that comes from playing with it. To enable the latter the company is adding the Inkling Playground in the Tinker console: a developer-facing interface for chatting with Inkling.
Capabilities
Real-world applications require models with a wide range of capabilities that can be combined and improved with fine-tuning. Thinking Machines is showcasing what Inkling can do and how it measures up on important qualities such as trustworthiness and safety.
Generalist Model
Inkling is designed to be broad. Thinking Machines Lab trained it across agentic, reasoning, coding, instruction-following, factuality, vision, and audio tasks, rather than narrowly optimizing for one domain. That breadth matters for customization and real-world use: different users need models that can adapt to very different workflows, not just excel on benchmarks.
Agentic Coding and Tool Use
A strong base for fine-tuning needs to flexibly solve a wide variety of tasks with agentic tool use. Inkling scores well among open-weights models on most agentic benchmarks.
Thinking Machines Lab trained Inkling to run inside a variety of coding and agent harnesses, and the company randomized the tool set and schema during training to reduce sensitivity to any particular one. Inkling’s controllable thinking effort, described in the next section, can be set from within the harness.
Controllable Thinking Effort
Test-time scaling and problem-solving are the core capability of every model, but that capacity is hard to capture with a single number. Developers fine-tuning models for a specialized task care as much about efficiency as about the max-effort performance on a public benchmark. Cost and latency are often binding constraints in real-world applications, and low latency in particular is crucial for enabling collaboration and improvement through iteration.
Sweeping Inkling’s effort setting from 0.2 to 0.99 traces its performance against mean generated tokens on Terminal Bench 2.1, HLE, and IFBench; competing models are shown at their default operating point. Inkling reaches a given score at fewer tokens — for example, it matches Nemotron 3 Ultra on Terminal Bench 2.1 at roughly a third of the tokens. *Humanity’s Last Exam scores reflect an earlier checkpoint and run slightly below the final release.
Inkling supports controllable thinking effort, allowing you to balance performance with token efficiency. The chart above shows the effort/performance curve of Inkling as well as other open-weights models on a range of benchmarks: Terminal Bench 2.1 for agentic coding, HLE for advanced reasoning, and IFBench for instruction following. Inkling spends one third as many tokens to achieve the same performance as Nemotron 3 Ultra on Terminal Bench. Cost and latency matter for a model that you run millions of times and as part of longer workflows; looking at the full cost curve allows developers to choose the best model for each use case.
Multimodality
A major goal of Inkling’s design is to serve as the background reasoning model in the interaction models system the company recently introduced. Interaction models enable the user to collaborate naturally, using voice and vision in real time. This requires a model natively trained for broad multimodal capabilities.
The multimodal components were trained from scratch on general-domain data. Thinking Machines Lab opted for an encoder-free architecture for audio and vision inputs, consistent with the interaction model design. Audio signals are input as dMel spectrograms, while images are encoded as patches of 40×40 pixels using a four-layer hMLP. Both are transformed via a light-weight embedding layer and processed jointly with text tokens.
Inkling transcribes speech, follows spoken instructions, answers questions about recordings, and reasons over longer-form audio. These capabilities place it among the strongest open-weights audio models on VoiceBench, MMAU, and AudioMC. For vision, Inkling accepts images as input and can describe visual content, answer questions, and perform in-depth reasoning based on the provided visual information. It demonstrates strong performance on charts, diagrams, and mathematical visual reasoning tasks. During inference, Inkling can also leverage a Python tool to support image understanding through operations such as zooming and cropping, while seamlessly integrating visual reasoning with code-based reasoning.
As Thinking Machines Lab’s first release, Inkling establishes a robust multimodal foundation for future work. The company expects its multimodal capabilities to continue improving as the model and training pipeline is expanded in subsequent iterations.
Learn more about Inkling here.
Source: Thinking Machines Lab
The post Thinking Machines Launches Open-Weight ‘Inkling’ Foundation Model for Fine-Tuning appeared first on AIwire.
