Model Selection
Endpoint for fetching all available models.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
application/json Query Parameters
Accepted but currently ignored: the page size is fixed at 25 regardless of the value sent. Use page to retrieve the remaining results.
Page number, starting at 1. The response is paginated: a single call returns at most 25 models, so a client that reads only the first page will miss models when meta.last_page is greater than 1. Iterate until meta.current_page equals meta.last_page to obtain the full catalogue.
Comma-separated list of inference types to filter by. Example: txt2img,txt2audio. Values must match the inference_types strings returned by this endpoint exactly — note that some of them use hyphens (img-upscale, img-rmbg, vid-upscale, video-replace). An unrecognised value is not rejected: the endpoint returns an empty data array.
txt2img, img2txt, txt2audio, txt2music, txt2video, img2video, img2img, audio2video, video-replace, img-upscale, img-rmbg, vid-upscale, txt2embedding, audio2text, video2text, audio_file2text, video_file2text Response
List of available models.
List of available models