list_base_models

List the base AI models available for generation in a workspace.

Sourced from the model registry and the workspace's feature config — not the Style table —
so every enabled base model is listed. Results are ranked by the requested `sort`, which
defaults to Layer's curated recommendation order.

To choose a model for a task, pass `filter.use_case` (and any required capabilities) and
take the first result. When the task has craft knowledge attached to it — pixel art,
storyboards, seamless textures, and similar — load the matching `model-guidance` skill for
prompt and workflow technique before generating.

IMPORTANT: Call tool `get_instructions` first for general platform guidance.

Parameters

Parameter	Type	Default	Description
filter	ModelQueryFilter	—	Query filters
fulltext	string	—	Search model name/description
modality	enum	—	Filter by modality: image, video, three_d, audio One of: image, video, three_d, audio
capabilities	CapabilityFilter	—	Filter by model capabilities
supports_reference_images	boolean	—	Set true to require at least one supported guidance file type — any type at all, so this alone does not guarantee any particular one. Omit (don't set false) to skip this filter
image_editing	boolean	—	Set true to require image-editing support — models that take a source image plus reference images to reproduce subjects from. Use this when generating new art that must match provided references. Omit to skip
style_reference	boolean	—	Set true to require style-reference (IP-Adapter `prompt` type) support — legacy style-only transfer that does not reproduce subjects. Omit (don't set false) to skip this filter
character_pose	boolean	—	Set true to require character pose reference images. Omit to skip
structure	boolean	—	Set true to require depth/structure reference images. Omit to skip
outline	boolean	—	Set true to require edge/outline reference images. Omit to skip
line_art	boolean	—	Set true to require line art reference images. Omit to skip
square	boolean	—	Set true to require 1:1 square output; omit to skip
portrait_9_16	boolean	—	Set true to require 9:16 portrait output; omit to skip
landscape_16_9	boolean	—	Set true to require 16:9 landscape output; omit to skip
multiple_aspect_ratios	boolean	—	Set true to require more than one aspect ratio; omit to skip
inpainting	boolean	—	Set true to require inpainting support. Omit (don't set false) to skip this filter
outpainting	boolean	—	Set true to require outpainting support; omit to skip
tileability	boolean	—	Set true to require seamless tileable textures; omit to skip
negative_prompt	boolean	—	Set true to require negative prompt support; omit to skip
generate_audio	boolean	—	Set true to require audio generation with video; omit to skip
lipsync	boolean	—	Set true to require lip-sync in video; omit to skip
video_effects	boolean	—	Set true to require video effects; omit to skip
text_to_3d	boolean	—	Set true to require text-to-3D; omit to skip
image_to_3d	boolean	—	Set true to require image-to-3D; omit to skip
textures	boolean	—	Set true to require textured 3D models; omit to skip
text_to_speech	boolean	—	Set true to require text-to-speech; omit to skip
sound_effect	boolean	—	Set true to require sound effect generation; omit to skip
use_case	enum	—	Filter to models that declare this use case, e.g. text_to_image, image_editing, image_to_video, upscaling. This is the primary way to narrow a task-shaped request. One of: text_to_image, image_editing, multi_angle, inpainting, reframing, split_into_layers, text_to_video, image_to_video, video_editing, video_extend, video_subtitle, video_lipsync, image_to_video_lipsync, text_to_3d, image_to_3d, remesh, retexture, uv_unwrap, animate, rig, segment, image_segment, text_to_speech, sound_effects, music, upscaling, video_interpolation, denoise_image, denoise_video, deblur_video, restore_image, sdr_to_hdr_video, background_removal, vectorization, virtual_try_on
provider	string	—	Filter by provider slug, e.g. 'bfl', 'google'. Case-insensitive.
featured_only	boolean	—	Set true to return only models in the curated featured set. Omit to include everything.
max_price	number>0	—	Exclude models whose average Creative Units per generation exceed this value.
released_after	string (date)	—	Exclude models publicly released on or before this date (ISO 8601, e.g. 2026-01-01).
sort	enum	recommended	Result ordering. 'recommended' (default) uses Layer's curated ranking for the requested use case or modality, falling back to quality score then popularity for uncurated models; 'elo' orders by Artificial Analysis quality score; 'popularity' by usage on Layer; 'newest' by public release date. One of: recommended, elo, popularity, newest
pagination	PaginationInput	—	Parameters driving result pagination
limit	integer1–100	20	Maximum number of results to return
cursor	string	—	Cursor from which to return results
workspace_idrequired	string (uuid)	—	The user's workspace id.