Trinity-Large-Preview leaves OpenRouter after 3.3T tokens
- Source
- x.com
- Date
An update on Trinity-Large-Preview: We are officially sunsetting the hosted preview endpoint on OpenRouter. The preview model has served over 3.3T tokens since it's launch in late January. A final thank you to everyone who used it. If you still have active pipelines targeting the preview endpoint, consider transitioning them to Trinity-Large-Thinking to avoid any service disruption. As a reminder, Trinity-Large-Thinking is free on @OpenRouter until 5/23. https://t.co/a9oVQkIfPn
As always, the weights for Preview will remain permanently available on @huggingface for local deployments and self-hosting. We're deeply grateful to everyone who built with the preview and shared feedback. Your early testing and usage helped us shape what became Trinity-Large-Thinking. https://t.co/9kyz4uxJZj
Context
Arcee AI is sunsetting its hosted Trinity-Large-Preview endpoint on OpenRouter, per its own post, after what it says was over 3.3 trillion served since the model launched in late January. Arcee directs anyone with a pipeline on the preview endpoint to move to Trinity-Large-Thinking, which it had made free on OpenRouter for a window, to avoid a service break. The Preview weights themselves remain on Hugging Face for local deployment or self-hosting.
- 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.
Checking sign-in…
Loading comments…