Released 2026-06-07. Newer AI models for workflow AI tasks, and a heads-up for retiring ones.
Added
- Latest Google Gemini models. Gemini AI tasks now offer Gemini 3.5 Flash (the new default), Gemini 3.1 Flash-Lite, and Gemini 3.1 Pro for text and structured output.
- Newer image generation. Text-to-image tasks add Google's latest native image models (Gemini 3.1 Flash Image and Gemini 3 Pro Image), and Together image tasks add FLUX.2 Pro for text-to-image and Qwen Image 2.0 for image editing.
Changed
- Older models are being retired by their providers. Google is sunsetting the Gemini 2.5 models and Imagen 4, and Together is phasing out FLUX.1 Schnell. New tasks use the newer models above by default. An existing task still set to a retiring model keeps working until that provider's end date — switch it to a current model before then. Affected workflow owners are notified by email with a link to each task.