Inkling from Thinking Machines is now available on AI Gateway
Source
vercel.com
Author
Rohan Taneja
Date
Why it matters
Inkling gives you an open-weights, multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition →mixture-of-expertsA model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.Full definition → with a 1M-token context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → and a dial for reasoning depth, so you can trade latency against thinking effort per call instead of switching models. Reachable today via Vercel's AI Gateway as thinkingmachines/inkling, which means no separate provider account or SDK to adopt it in an existing AI SDK app.
Terms in this piece · Glossary
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Key quotes
“Inkling is a broad generalist model, trained across agentic, reasoning, coding, instruction-following, factuality, vision, and audio tasks rather than optimized for a single domain.”
“AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.”
