Skip to content
ThreadOut
Thinking Machines@thinkymachines · Jul 15, 2026

Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making…

6 tweets1 min read♥ 14.9Koriginal

Summary

Introducing Inkling, a new multimodal AI model that efficiently reasons across text, image, and audio with open weights available for fine-tuning. The model offers flexible cost/performance tradeoffs through continuous thinking and performs particularly well on audio benchmarks.

Summarized by ThreadOut AI from the full thread. May miss nuance — read the thread below.

  1. #1

    Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. thinkingmachines.ai/news/introduci… Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵

  2. #2

    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.

  3. #3

    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.

  4. #4

    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.

  5. #5

    Inkling is the first in a family. We’ve included some details of Inkling-Small, a lighter-weight model trained on a similar recipe, with full weights to follow.

  6. #6

    We hope you enjoy Inkling, and as always we’re keen to see what you build.