--- title: README emoji: 🔑 colorFrom: yellow colorTo: green sdk: static pinned: false --- # apimodels.app [apimodels.app](https://apimodels.app/?utm_source=huggingface&utm_medium=org) is a multi-model API platform: one key and one endpoint for 170+ image, video, audio and language models, paid per use, with failed jobs not charged. Here we publish browser demos you can run with your own key, open datasets made with the API, and guides for calling hosted models. **Try in the browser** - [FlashVSR Video Upscaler](https://huggingface.co/spaces/apimodels/flashvsr-video-upscaler): upscale a clip to 720p, 1080p, 2K or 4K and compare before and after. - [Nemotron 3.5 Transcribe](https://huggingface.co/spaces/apimodels/nemotron-transcribe): speech to text in 40 languages, with timestamps and speaker labels. - [AI Video Generator](https://huggingface.co/spaces/apimodels/ai-video-generator): Veo 3.1, Kling 4.0, Seedance 2.5, plus image generation and editing. - [Nano Banana 2.1, free](https://huggingface.co/spaces/stimi/nano-banana-free): 2 free images a day after signing in with your Hugging Face account. **Data and write-ups** - [Chinese Idioms Drawn Literally](https://huggingface.co/datasets/apimodels/chinese-idioms-literal-illustrations): 36 illustrations with prompts, pinyin and English meanings (CC BY 4.0), and the [article on how they were made](https://huggingface.co/blog/stimi/drawing-chinese-idioms-literally). API docs: [apimodels.app/docs](https://apimodels.app/docs?utm_source=huggingface&utm_medium=org)