Thinky Machines Offers Free Inkling Models for Testing
Thinking Machines Lab researchers share access to Inkling models and request usage details.
Eric Zhang posted that Thinking Machines is hosting Inkling and Inkling-Small for free use inside any agent harness. A retweet from Ruiqi Zhong highlights a request for user reports on actual builds, model performance, and needed multimodal features. The posts come from lab members who previously worked at Anthropic and Modal. No further details on availability limits or timelines appear in the supplied lines.
Combined views
37.2K
4 posts, first seen 4d ago
Reactions from ranked influencers
4 posts
We care about the community and we'd love to learn how you're actually using Inkling! - What are you building with it? - Where does it feel strongest or weakest? - Which multimodal capabilities matter most to you? - If we made an Inkling Mini/Tiny, what size or sparsity would…
Models need to be smart and useful. We're building Inkling and Tinker to turn real workflows into better evals, models, and benchmarks---and we want your input!
Inkling and Inkling Small are now served directly by @thinkymachines on OpenRouter, free to use inside agentic harnesses only. Plug them into Claude Code, Codex, Hermes Agent and more to unlock the free access. Open-weight MoE reasoning models with native text, image, and…
We are hosting Inkling and Inkling-Small! Try it out, for free, in your favorite agent harness. :)
We want to improve Inkling’s agentic performance. To help us understand its real-world behavior, we are making it available for free on OpenRouter (only with agentic harnesses) for the next few weeks, starting now. We’ll use the data, disassociated from accounts, to better it.
Inkling and Inkling Small are now served directly by @thinkymachines on OpenRouter, free to use inside agentic harnesses only. Plug them into Claude Code, Codex, Hermes Agent and more to unlock the free access. Open-weight MoE reasoning models with native text, image, and…