# 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, audioOne 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. |