Models

This page is a hand-grouped index of the models CarrotHub exposes. Use it to pick the right endpoint, then jump into the corresponding API reference for the request/response schema.

​

LLM / Chat

Reachable via the OpenAI-compatible /v1/chat/completions alias or the provider-specific paths.

​

Image Generation (Text-to-Image)

​

Image Editing (Image-to-Image)

​

Video Generation (Berry All-in-One)

Berry models support text-to-video, first/last-frame image-to-video, and multimodal reference-to-video through a single generation endpoint. All four support 2–30 second videos, or duration: -1 for smart duration. Keyframe inputs (first_frame / last_frame) cannot be combined with reference inputs in the same request. See each reference for the generation endpoint, task status, and result schema.

​

Video Generation (Text-to-Video)

​

Video Generation (Image-to-Video)

​

Video Editing

​

Speech (Text-to-Speech)

​

Music (Text-to-Music)