models_list

List models with heavy fields stripped and deprecated capabilities filtered. Args: - filters: optional — privacy (private/public), status, modality (image/video/3d/audio), or type (server-side fine-grained, e.g. "flux.1-lora"). Modality filter is implemented as a client-side scan over `capabilities` — the API has no native modality filter, and `type=custom` models can span any modality. Scan cap mirrors the Scenario webapp: 500 for public, 100 for private. Use `filters.type` for cheaper server-side narrowing when you know the model family. - limit: results per page (default 20, max 100) - page_token: pagination token from a previous response (nextPaginationToken) - team_id, project_id: required for OAuth callers Returns: { models } array (heavy fields stripped — trainingProgress, parameters, trainingImages, trainingImagePairs, accessRestrictions, exampleAssetIds, custom, thumbnail; deprecated capabilities filtered) plus nextPaginationToken when more pages exist. Don't use when: you need to find a model by name or intent — prefer search with target="models".

{
  "filters": {
    "modality": "image",
    "status": "trained"
  },
  "limit": 20,
  "team_id": "team_abc123",
  "project_id": "proj_xyz789"
}

{
  "models": [
    {
      "id": "model_custom_abc",
      "name": "My Dragon Style",
      "status": "trained",
      "modality": "image"
    }
  ]
}