Skip to main content
​
2026.04.27

​
New video model: HappyHorse 1.0

Released dashscope/happyhorse-1.0 — a single model ID that covers text-to-video, image-to-video (first frame), reference-to-video (multi-image), and video editing (video + reference images), auto-dispatched by input shape.
  • Supports 720P / 1080P output, duration 3s–15s (video-edit mode follows the source video length, capped at 15s);
  • In reference-to-video mode, refer to the N-th image with character1, character2, … in the prompt;
  • Video-edit mode exposes extra_params.audio_setting (auto / origin) for audio handling;
  • Pricing: 720P 180 credits/second, 1080P 300 credits/second.
For full parameter details, see HappyHorse 1.0. For credit consumption, see Pricing.
​
2026.04.21

​
New video model: Kling v3 Motion Control

Released kling/kling-v3-motion-control — use the character from a reference image as the subject and replicate the motion from a reference video.
  • Requires both 1 character reference image and 1 motion reference video;
  • Supports 720P / 1080P output; the output duration equals the reference video duration;
  • Reference video duration: 3s–30s (depending on extra_params.character_orientation: video allows up to 30s, image up to 10s);
  • Pricing: 720P 180 credits/second, 1080P 220 credits/second.
For full parameter details, see Kling v3 Motion Control. For credit consumption, see Pricing.
​
2026.04.20

​
First batch of Open Platform models now live

imini Open Platform is officially live, with the first wave of image and video generation models available.

​
Image models

  • google/nano-banana: Based on Gemini 2.5 Flash Image. Fast and low-cost, supports up to 3 reference images.
  • google/nano-banana-pro: Based on Gemini 3 Pro Image. Supports up to 14 reference images, output up to 4K.
  • google/nano-banana-2: Based on Gemini 3.1 Flash Image. Supports up to 14 reference images, with 512 / 1K / 2K / 4K output.

​
Video models

  • kling/kling-v3: Kling 3.0 video generation. Supports 720P / 1080P with optional audio.
  • kling/kling-v3-omni: Kling 3.0 full-modality variant. Supports reference video input.
  • doubao/seedance-2.0: Doubao Seedance 2.0. Supports text-to-video, image-to-video, and multimodal references (image + video + audio).
  • doubao/seedance-2.0-fast: Seedance 2.0 Fast — the same capabilities at a lower cost.
For detailed parameter documentation, see the API Reference. For credit consumption, see Pricing.