Integrate state-of-the-art artificial intelligence into your applications with our comprehensive suite of APIs for language, vision, audio, and video processing.
Generate 3D models from your images using Hunyuan 3D.
Music generation model that creates original music from text descriptions.
Text-to-speech model with natural-sounding voices in multiple languages.
Image generation model that creates high-quality images from text descriptions.
Reve Image (Halfmoon): A model trained from the ground up to excel at prompt adherence, aesthetics, and typography.
The ChatFacile model, better known as Devoir Facile, is the most widely used AI education agent in France. The model is only accessible via API here for free. Its advantages include being free and responding quickly (in less than a second).
Conversational AI model with internet knowledge and coding capabilities.
Advanced text generation model for creative writing, content creation, and more.
Open-source large language model for general text generation and understanding.
Framepack is an efficient Image-to-video model that autoregressively generates videos.
Generate video clips from your prompts using Kling 2.0
Video generation model that creates short videos from text descriptions.
Our APIs make it simple to add cutting-edge AI capabilities to your applications. Start with 100 free credits and scale as you grow.