13-billion-parameter model generating cinema-quality videos with precise motion control, transitions, and special effects.
Free tier (verified July 2026): Free, including commercial use — catch: API access is $0.40 per 5-sec video
Some links may be affiliate links. We may earn a small commission at no extra cost to you. Learn more
13-billion-parameter model generating cinema-quality videos with precise motion control, transitions, and special effects.
Free tier (verified July 2026): Free, including commercial use — catch: API access is $0.40 per 5-sec video
Reviewed by Sohail Akhtar
Lead Editor & Founder
What we like
Limitations
✓ Free tier re-verified July 2026: Free, including commercial use — API access is $0.40 per 5-sec video
Completely free for commercial use. API: $0.40 per 5-second video.
Associated Tags
tencent hunyuan ai, 13b video model, cinema quality ai, motion control video, open source video ai, vfx video generator
Discover practical workflows and real-world scenarios where Hunyuan Video delivers key solutions.
Film and advertising pre-production teams generating concept video sequences before committing to live production
VFX artists creating motion reference footage and visual effects prototypes for client approval
Developers building automated video generation pipelines using the API for content platforms or marketing workflows
Researchers fine-tuning the open-source model weights for specialized video generation domains
Kling, Vidu, Veo 3, Runway and more — ranked on what their free plans actually allow.
Read the full comparison →Tencent's open-source AI model that generates interactive, action-controllable game video sequences from a single image and keyboard inputs.
Open-source AI model by Tencent that generates explorable, interactive 3D worlds from text or image inputs using panoramic scene reconstruction.
Tencent's 13B model excels at 256K context reasoning, multilingual agents, and search.
Skywork AI's 1.8B open-source interactive world model generating real-time 25 FPS gameplay from keyboard and mouse inputs, with long-sequence consistency and free weights on GitHub and Hugging Face.