Inkling ships with open weights and native text, image, and audio reasoning
- Source
- x.com
- Date
Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. https://t.co/Ghebq5mG30 Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵
Cost and latency are important in real-world use cases. Inkling's continuous thinking effort lets you pick your point on the cost/performance curve—reaching the same score with a fraction of the tokens.
Inkling natively understands and reasons across text, audio, and images. It’s strong on audio in particular, ranking among the strongest open-weights models on VoiceBench, MMAU, and AudioMC.
We’re grateful to our partners for their day-0 support across the open-source ecosystem: @togethercompute, @FireworksAI_HQ, @databricks, @UnslothAI, @modal, @baseten, @lightseekorg, @inferact on VLLM, @radixark on SGLang.
Context
Inkling gives developers a downloadable model for working across text, images and audio, with customization available through Tinker, Thinking Machines' training service. The July 15, 2026 release positions it as a foundation developers can adapt to their own tasks.
Its adjustable thinking effort lets a developer choose how much reasoning the model performs before answering, trading computation against performance. Combined with access to the model weights, that gives developers control over both customization and how much work an answer consumes. The lab presents this combination as Inkling's advantage and explicitly says it is not the strongest overall model available. Release rationale.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Checking sign-in…
Loading comments…