Models you can run on the canvas today.
Every model listed here runs natively on a PlugNode node. Bring your own Gemini, OpenAI, or ElevenLabs key and you pay providers directly.
Text-to-video and image-to-video
Google Veo models run through the Video node. Generate up to 4K with native audio, wire into a pipeline, publish the flow behind a signed URL.
Text-to-image and edit-by-description
Google’s Gemini image family runs on the Image node: Nano Banana, Nano Banana Pro, and Gemini 3.1 Flash Image. Generate, edit, or compose from references.
Text-to-speech
ElevenLabs and Gemini voices run through the Audio node. Bring your own API key and pay providers directly.
Chat and reasoning
Gemini and OpenAI text models power the Text node. Dedicated per-model pages land as search demand justifies them.
More models land as dedicated nodes ship. Non-native vendors (Flux, Kling, Sora, Ideogram, Recraft) are on the roadmap. We do not list them here until the node is real.