Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.stagewise.io/llms.txt

Use this file to discover all available pages before exploring further.

stagewise ships with a curated list of built-in models, but you can define additional models that route to any configured endpoint — built-in or custom.

​
Adding a custom model

1

Open Models & Providers

Navigate to Settings → Agent → Models & Providers and scroll to the Custom Models section.
2

Click Add model

Click Add model to open the model editor dialog.
3

Configure the model

Enter all the necessary information for the model and hit Save.

​
Model capabilities

Each model that get’s registered must support the following set of capabilities in order to be usable within stagewise:
  • Text –– Standard text generation
  • Tool Calling –– Standardized tool generation via API
Models that don’t support the required capabilities will fail at runtime.
The model may optionally support the following modalities and capabilities.
  • Image Vision –– Image type inputs
  • Video Vision –– Video type inputs
  • Audio –– Audio type inputs for hearing capabilities
The stagewise agent does NOT need any of these model/API capabilities to fully operate:
  • File Inputs –– stagewise reads files with a custom pipeline that’s independent of native API capabilities

​
Custom model with a custom endpoint

A typical workflow for self-hosted models:
  1. Create a custom endpoint pointing to your local server (e.g. http://localhost:11434/v1 for Ollama)
  2. Create a custom model with the correct model ID for that server
  3. Select the custom model from the model picker in the chat sidebar

​
Provider options and headers

Advanced users can specify raw provider options (JSON) and custom HTTP headers for a model. These are passed directly to the AI SDK and can control provider-specific behavior like reasoning effort, thinking budgets, or streaming options.