NodeTool Cloud is in alpha — run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it →
Product
StudioCloud (alpha)AgentsNode-based workflowsAI video editorAI image editorStoryboardsMCP serverSupported modelsDownloadSolutions
DevelopersMarketingGame developmentLocal-firstResearchersAll solutionsResources
TemplatesRecipesPresetsAd libraryCompare alternativesFAQBAGEL in a visual AI workflow
Run ByteDance Seed's BAGEL in a visual AI workflow: one 7B model that generates, edits, and understands images, at provider list price.
Fresh BAGEL examples are on the way. Meanwhile, here's the NodeTool canvas where you'll run it.
BAGEL is a unified multimodal model from ByteDance Seed. A single 7B parameter model generates images, edits images, and understands images.
The node has a task input to choose between those modes, and a thinking toggle. That makes it a compact option when a graph needs both a generation step and an image understanding step.
NodeTool is bring-your-own-key, so you call BAGEL through a provider you already use and pay that provider's list price. The table below lists the providers that serve it and the model ids their `--list-models` output reports.
Where to run BAGEL
NodeTool is bring-your-own-key: you call BAGEL through a provider you already have access to and pay their list price — no credits, no markup. These providers serve BAGEL today.
Frequently asked questions
- What can BAGEL do?
- Generate images, edit images, and answer questions about images, all from one 7B parameter model.
- How do I switch between generating and editing?
- Set the task input on the node and pass an image when you want to edit or ask about one.
- What does BAGEL cost in NodeTool?
- NodeTool adds no per-image fee. You pay the provider that serves BAGEL at its list price, with your own key.
Run BAGEL your way.
Download NodeTool Studio and build across image, video, audio, and text with your own keys.