List configured image providers and whether their API key is present.

A provider only appears as configured: true once its key env var is set. Use the returned id values as the prefix in provider:model specs.

Discover image-capable models offered by configured providers.

Queries each provider's model endpoint, filters to image models, and caches the result on disk. Set refresh=true to bypass the cache. Pass provider to query just one provider.

Register any OpenAI-compatible image endpoint and remember it for later.

Use this when the user names an endpoint like https://api.example.com/v1. The server probes {base_url}/models, figures out which models can produce images, saves the provider to the config file, and makes it available to generate_image immediately and on every future run.

Parameters

id: Short handle used in provider:model specs (e.g. example). Lowercase letters, digits, - and _. base_url: The OpenAI-compatible API root, e.g. https://api.example.com/v1. api_key: Optional bearer token, stored in the gitignored config file so it survives restarts. Prefer api_key_env if you would rather keep the secret in an environment variable. api_key_env: Name of an env var holding the key (ignored when api_key is given). Leave both unset for endpoints that need no auth. default_model: Model id to use by default. If omitted and exactly one image model is found, it is selected automatically. dialect: auto (default), images (/images/generations) or chat (/chat/completions with image modalities). auto uses the Images API and transparently falls back to chat-completions on 404/405. make_default: Also set this provider's model as the global default model. discover: Set false to skip the /models probe (required for endpoints that do not implement it).

Returns the discovered models plus any warnings; inspect models and, if there are several, call set_default_model to choose one.

Remove a provider (including built-in presets) from the config file.

Persist the model used when generate_image is called without one.

model is a provider:model spec or an alias, e.g. example:flux-schnell. The choice is saved to the config file so it applies to future runs.

Generate an image, or edit existing images, via an OpenAI-compatible provider.

Model selection

model accepts three forms:

• provider:model — explicit, e.g. openrouter:google/gemini-3.1-flash-image-preview, openai:gpt-image-1, xai:grok-imagine-image-2.0. Fastest and unambiguous.

• a bare model id — searched across every configured provider's catalogue (run list_models first). Ambiguous ids raise an error listing candidates.

• an alias — defined in providers.json (e.g. nb2).

If omitted, the configured default model is used.

Editing

Pass input_image_path (and optionally input_image_paths) and the prompt becomes an edit instruction. Requirements vary by provider.

Output

Images are always written to disk and their paths returned. Set return_image_content=true to additionally embed the images in the tool result so the model can look at them.