> ## Documentation Index
> Fetch the complete documentation index at: https://www.carrothub.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Every model available through the CarrotHub API, grouped by capability

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.

| Family | How to call it |
| - | - |
| OpenAI GPT | [`/v1/chat/completions`](https://www.carrothub.ai/docs/api-reference/endpoint/openai/chat) |

## Image Generation (Text-to-Image)

| Model | Highlights | Reference |
| - | - | - |
| `openai/gpt-image-2` | 4K, 1–4 images per call | [GPT Image 2](https://www.carrothub.ai/docs/api-reference/endpoint/openai/gpt-image-2/generation.md) |
| `google/nano-banana-pro` | Pro tier | [Nano Banana Pro](https://www.carrothub.ai/docs/api-reference/endpoint/google/nano-banana-pro/generation.md) |
| `google/nano-banana-2` | 4K, web-search grounding | [Nano Banana 2](https://www.carrothub.ai/docs/api-reference/endpoint/google/nano-banana-2/generation.md) |
| `alibaba/wan2.6-t2i` | Batch, negative prompt, seed | [Wan 2.6 T2I](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.6-t2i/generation.md) |
| `alibaba/wan2.5-t2i-preview` | Prompt extension | [Wan 2.5 T2I Preview](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.5-t2i-preview/generation.md) |
| `alibaba/qwen-image-max` | Qwen-family image gen | [Qwen Image Max](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/qwen-image-max/generation.md) |
| `midjourney/diffusion` | One-prompt, high quality | [Midjourney](https://www.carrothub.ai/docs/api-reference/endpoint/midjourney/diffusion.md) |

## Image Editing (Image-to-Image)

| Model | Highlights | Reference |
| - | - | - |
| `openai/gpt-image-2/edit` | Mask-based edits, 4K | [GPT Image 2 Edit](https://www.carrothub.ai/docs/api-reference/endpoint/openai/gpt-image-2/edit.md) |
| `google/nano-banana-pro/edit` | Pro-tier edit | [Nano Banana Pro Edit](https://www.carrothub.ai/docs/api-reference/endpoint/google/nano-banana-pro/edit.md) |
| `google/nano-banana-2/edit` | Up to 14 reference images | [Nano Banana 2 Edit](https://www.carrothub.ai/docs/api-reference/endpoint/google/nano-banana-2/edit.md) |
| `alibaba/wan2.6-image` | Image-to-image transform | [Wan 2.6 Image](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.6-image/generation.md) |
| `alibaba/wan2.5-i2i-preview` | Preview-tier transform | [Wan 2.5 I2I Preview](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.5-i2i-preview/generation.md) |
| `alibaba/qwen-image-edit-max` | Qwen Edit Max | [Qwen Image Edit Max](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/qwen-image-edit-max/generation.md) |

## 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.

| Model | Highlights | Reference |
| - | - | - |
| `berry-1.0` | 480p / 720p / 1080p, audio output | [Berry 1.0](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/berry-1.0/generation.md) |
| `berry-1.0-turbo` | Faster standard tier, 480p / 720p / 1080p, audio output | [Berry 1.0 Turbo](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/berry-1.0-turbo/generation.md) |
| `berry-1.0-pro` | 1080p / 2K / 4K, audio output | [Berry 1.0 Pro](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/berry-1.0-pro/generation.md) |
| `berry-1.0-pro-turbo` | Faster Pro tier, 1080p / 2K / 4K, audio output | [Berry 1.0 Pro Turbo](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/berry-1.0-pro-turbo/generation.md) |

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)

| Model | Highlights | Reference |
| - | - | - |
| `alibaba/wan2.6-t2v` | Multi-resolution, audio, multi-shot | [Wan 2.6 T2V](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.6-t2v/generation.md) |
| `alibaba/wan2.5-t2v-preview` | Audio support | [Wan 2.5 T2V Preview](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.5-t2v-preview/generation.md) |
| `alibaba/wan2.2-t2v-plus` | 5-second clips | [Wan 2.2 T2V Plus](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.2-t2v-plus/generation.md) |
| `carrothub/wan2.6-t2v-spark` | Spark accelerated tier | [Wan 2.6 T2V Spark](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/wan2.6-t2v-spark/generation.md) |
| `carrothub/wan2.5-t2v-spark` | Spark accelerated tier | [Wan 2.5 T2V Spark](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/wan2.5-t2v-spark/generation.md) |
| `klingai/kling-v3-omni/text-to-video` | Kling Omni | [Kling V3 Omni T2V](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3-omni/text-to-video.md) |
| `klingai/kling-v3/text-to-video` | Kling V3.0 | [Kling V3 T2V](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3/text-to-video.md) |
| `midjourney/video-diffusion` | 480p / 720p | [Midjourney Video](https://www.carrothub.ai/docs/api-reference/endpoint/midjourney/video-diffusion.md) |

## Video Generation (Image-to-Video)

| Model | Highlights | Reference |
| - | - | - |
| `alibaba/wan2.6-i2v` | 1080P, audio | [Wan 2.6 I2V](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.6-i2v/generation.md) |
| `alibaba/wan2.5-i2v-preview` | Audio support | [Wan 2.5 I2V Preview](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.5-i2v-preview/generation.md) |
| `alibaba/wan2.2-i2v-plus` | 1080P | [Wan 2.2 I2V Plus](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.2-i2v-plus/generation.md) |
| `alibaba/wan2.2-i2v-flash` | Speed-optimized | [Wan 2.2 I2V Flash](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.2-i2v-flash/generation.md) |
| `alibaba/wan2.1-kf2v-plus` | Keyframe interpolation | [Wan 2.1 KF2V Plus](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.1-kf2v-plus/generation.md) |
| `carrothub/wan2.6-i2v-spark` | Spark accelerated tier | [Wan 2.6 I2V Spark](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/wan2.6-i2v-spark/generation.md) |
| `carrothub/wan2.5-i2v-spark` | Spark accelerated tier | [Wan 2.5 I2V Spark](https://www.carrothub.ai/docs/api-reference/endpoint/carrothub/wan2.5-i2v-spark/generation.md) |
| `klingai/kling-v3-omni/image-to-video` | Kling Omni | [Kling V3 Omni I2V](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3-omni/image-to-video.md) |
| `klingai/kling-v3-omni/reference-image-to-video` | Reference-driven | [Kling V3 Omni Ref I2V](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3-omni/reference-image-to-video.md) |
| `klingai/kling-v3/image-to-video` | Kling V3.0 | [Kling V3 I2V](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3/image-to-video.md) |

## Video Editing

| Model | Highlights | Reference |
| - | - | - |
| `klingai/kling-v3-omni/reference-video-to-video` | Reference-image to video | [Kling V3 Omni Ref V2V](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3-omni/reference-video-to-video.md) |
| `klingai/kling-v3-omni/video-to-video-edit` | Prompted video editing | [Kling V3 Omni V2V Edit](https://www.carrothub.ai/docs/api-reference/endpoint/klingai/kling-v3-omni/video-to-video-edit.md) |
| `alibaba/wan2.1-vace-plus` | Outpainting / inpainting / extension | [Wan 2.1 VACE Plus](https://www.carrothub.ai/docs/api-reference/endpoint/alibaba/wan2.1-vace-plus/generation.md) |

## Speech (Text-to-Speech)

| Model | Highlights | Reference |
| - | - | - |
| `minimax/speech-2.8-hd` | HD, emotion control, 37+ languages | [Speech 2.8 HD](https://www.carrothub.ai/docs/api-reference/endpoint/minimax/speech-2.8-hd/text-to-speech.md) |
| `minimax/speech-2.8-turbo` | Low-latency variant | [Speech 2.8 Turbo](https://www.carrothub.ai/docs/api-reference/endpoint/minimax/speech-2.8-turbo/text-to-speech.md) |

## Music (Text-to-Music)

| Model | Highlights | Reference |
| - | - | - |
| `minimax/music-2.5` | Auto-lyrics, up to 5 minutes | [Music 2.5](https://www.carrothub.ai/docs/api-reference/endpoint/minimax/music-2.5/text-to-music.md) |
| `minimax/music-2.0` | Classic version | [Music 2.0](https://www.carrothub.ai/docs/api-reference/endpoint/minimax/music-2.0/text-to-music.md) |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.