AI Video APIAI Video API

Video Generation

  • MiniMax H3 SH — Open Weights text, first/last frames, and multimodal references; 3–15 seconds at 480p/540p/768p/1080p with native stereo audio, from 8 credits/s

  • Kling 3.0 Official Protocol — Official text, first-frame, and first/last-frame endpoints, with 4K and state callbacks

  • Kling 3.0 Omni — Current Kling protocol for generation, references, and video editing

  • Kling 3.0 Turbo — Official text-to-video and first-frame protocol, with audio, 720p/1080p, and 3–15 second output

  • MiniMax H3 Fast — 5–15 second 480p text-to-video, first/last frames, and multimodal references; all input materials are free

  • MiniMax H3 Max Turbo — 5–15 second text-to-video and first/last frames at 480p or 768p, with prompt expansion and an optional seed; from 6.54 credits/s

  • MiniMax H3 Max — Fast 5–15 second text-to-video and first/last-frame generation at 480p or 768p; input images are free

  • MiniMax H3 — Native multimodal text, image, video, and audio reference generation at 2K and 768p

  • Long Video — Create consistent 4–180 second videos with HappyHorse or Seedance

  • Seedance 2.5 — 480p/720p/1080p output, duration=-1 with or without video input, up to 30-second output, audio-only input, and MP4/MOV

  • Seedance 2.0 — Multi-modal video generation with text, image, video, and audio references

  • Seedance 2.0 Fast — Faster Seedance 2.0 with lower pricing

  • Seedance 1.5 Pro — Text-to-video, first-frame, and first-and-last-frame video generation

  • HappyHorse 1.1 — Alibaba video generation and editing with text-to-video, image-to-video, reference-to-video, and video-edit modes

  • HappyHorse 1.0 — Alibaba video generation and editing with text-to-video, image-to-video, reference-to-video, and video-edit modes

  • Music Video Generator — Audio plus reference photos to lip-synced music videos, up to 10 minutes

  • Music to Video Pro — Revid ai-video/pro music videos with reference images, subtitles, ratio, resolution-based pricing, and lyrics lip sync

  • Kling 2.6 — Kling 2.6, image-to-video with optional audio

  • Kling 3.0 — Kling 3.0, text-to-video with standard and professional modes

  • Veo 3.1 — Google Veo 3.1, text-to-video, image-to-video, with background music

  • Grok Imagine — xAI Grok Imagine, text-to-video and image-to-video with fun/normal/spicy modes

  • Wan 2.6 — Alibaba Wan 2.6, text-to-video, image-to-video, and reference-to-video

  • Wan 2.7 — Alibaba Wan 2.7, text-to-video, image-to-video, reference-to-video, and video editing with synced audio