Models

The Agent, Create, and Code nodes all run on generative models you install into your Runchat account. Models come from Fal (image, video, 3D, audio) and OpenRouter (text and reasoning), with a small number of additional providers proxied through Fal.

​

Selecting a model

Each Agent, Create, and Code node has a model dropdown in its settings bar. Click it to open the model picker filtered to models compatible with that node type. The picker groups models by modality (edit image, create image, create 3D, create video, agent, other), and within each group sorts by popularity. You can switch the sort to cost, type, or name, or filter by tags and category. The Create node picker shows image, video, audio, 3D and other media-producing models. The Agent and Code pickers show text and reasoning models.

​

Installing models

You install models from the Add Nodes panel in the editor sidebar, filtered to Models. There are two ways to add a new one:

• Install from Fal or Openrouter: a button at the top of the Models filter that opens a search across the Fal and OpenRouter catalogues. Find the model you want and click Install.
• Paste a model URL: paste a URL from fal.ai/models/... or openrouter.ai/models/... directly into the Search bar in the Add Nodes panel. Runchat parses the URL and offers to install the model.

Most models become available immediately after installing. A small number need to be manually verified by the Runchat team before they’re enabled, in which case the model will appear in your library but won’t be runnable until verification completes.

​

Picking the right model

Cheaper models are usually faster but less reliable for complex reasoning, multi-step tool calls, or tight quality demands. A common workflow:

1. Iterate on a cheap, fast model (Runchat Image for images, MiMo for text)
2. Once the workflow is right, swap to a higher-quality model (NanoBanana Pro, Imagen 4 Pro, Flux 2 Pro, Claude Opus) for the final pass

See Credits → Model pricing for a full cost comparison across all default models.

​

Scope and removal

Installed models are scoped per user. They’re available in every workflow you create, regardless of team. Team admins can apply a model whitelist to restrict what team members can install. To remove models, disconnect the corresponding provider integration from your account.

​

Next steps

• Credits: how model usage is priced
• Credentials: link your own API keys to bill providers directly
• Create node: use installed image, video, and 3D models
• Agent node: use installed text and reasoning models