Models /Videos

Videos

Pick a model below. Each model exposes its own endpoints (text-to-image, image-to-image, etc.) at /api/v2/{model}{/operation}.

Showing 1–22 of 22

Kling 3 Pro preview

Kling 3 Pro

4 endpoints

Latest Kling model with high quality video generation

Text to VideoImage to VideoMotion ControlReference to Video
/api/v2/kling-3
Influencer
Happy Horse 1.1 preview

Happy Horse 1.1

3 endpoints

Happy Horse 1.1: 1080p video with synchronized native audio and multilingual lip-sync. Supports text-to-video, image-to-video, reference-to-video, and video-edit.

Text to VideoImage to VideoReference to Video
/api/v2/happy-horse
Influencer
Omni Flash preview

Omni Flash

3 endpoints

Cinematic video with 720p–4K output. Text-to-video and multi-reference image-to-video via Atlas Cloud.

Text to VideoImage to VideoReference to Video Omni
/api/v2/gemini-omni
Influencer
Seedance 2.5 preview

Seedance 2.5

4 endpoints

Seedance 2.5 with native audio-video sync, clips up to 30 seconds, ultrawide aspect ratios, and omni-reference across images, video, and audio.

Text to VideoImage to VideoTalking HeadReference to Video Omni
/api/v2/seedance-2.5
Influencer
Seedance 2.0 preview

Seedance 2.0

5 endpoints

Seedance 2.0 with native audio-video sync, advanced camera control, and up to 1080p resolution.

Text to VideoImage to VideoTalking HeadReference to Video OmniExtend Video
/api/v2/seedance-2
Influencer
Pricing 50 cr / second
Kling 2.6 Pro preview

Kling 2.6 Pro

2 endpoints

Kling v2.6 Pro video generation

Text to VideoImage to Video
/api/v2/kling-2.6
Veo 3.1 Fast preview

Veo 3.1 Fast

3 endpoints

Veo 3.1 video generation

Text to VideoImage to VideoTalking Head
/api/v2/veo-3.1
Wan 2.7 preview

Wan 2.7

2 endpoints

Wan 2.7 with enhanced motion smoothness and scene fidelity

Text to VideoImage to Video
/api/v2/wan-2.7
Wan 2.6 preview

Wan 2.6

2 endpoints

Wan 2.6 video generation

Text to VideoImage to Video
/api/v2/wan-2.6
MHVideos

MiniMax H3

4 endpoints

MiniMax H3: multimodal 2K video with native stereo audio. Text-to-video, image-to-video (first + last frame), and reference-to-video (up to 9 images / 3 clips / 3 audio refs).

Text to VideoImage to VideoTalking HeadReference to Video
/api/v2/minimax-h3
Influencer
F3Videos

Flux 3

2 endpoints

Flux 3: native-audio video with first/last frame control, up to 20s and 1080p.

Text to VideoImage to Video
/api/v2/flux-3
MiniMax Hailuo-02 Pro preview

MiniMax Hailuo-02 Pro

2 endpoints

Hailuo-02 Pro video generation

Text to VideoImage to Video
/api/v2/minimax-hailuo
Kandinsky 5.0 Pro preview

Kandinsky 5.0 Pro

2 endpoints

Kandinsky 5.0 Pro video generation

Text to VideoImage to Video
/api/v2/kandinsky-5
Grok Imagine Video preview

Grok Imagine Video

2 endpoints

Grok Imagine video generation

Text to VideoImage to Video
/api/v2/grok-imagine-video
Wan 2.2 5B preview

Wan 2.2 5B

2 endpoints

Wan 2.2 5B with fewer restrictions

Text to VideoImage to Video
/api/v2/wan-2.2
Hunyuan Video preview

Hunyuan Video

2 endpoints

Hunyuan video generation

Text to VideoImage to Video
/api/v2/hunyuan-video
Luma Dream Machine Ray2 preview

Luma Dream Machine Ray2

2 endpoints

Luma Dream Machine Ray 2 video generation

Text to VideoImage to Video
/api/v2/luma-ray-2
Magi preview

Magi

2 endpoints

Magi video generation

Text to VideoImage to Video
/api/v2/magi
LTX-2 19B preview

LTX-2 19B

2 endpoints

LTX-2 19B Distilled high-quality video generation

Text to VideoImage to Video
/api/v2/ltx-2-19b
LTX 2.3 Fast preview

LTX 2.3 Fast

2 endpoints

Fast LTX 2.3 video generation with audio, up to 4K and 20s duration

Text to VideoImage to Video
/api/v2/ltx-2.3
LTX 2.3 Pro preview

LTX 2.3 Pro

2 endpoints

High-fidelity LTX 2.3 Pro video generation with audio, up to 4K and 48fps

Text to VideoImage to Video
/api/v2/ltx-2.3-pro
WAN 2.2 + LoRA preview

WAN 2.2 + LoRA

2 endpoints

WAN 2.2 14B with custom LoRA weights. Pass high-noise + low-noise variants together for best results.

Text to VideoImage to Video
/api/v2/wan-2.2-lora
Sync