Call best-in-class open and hosted models for image, video, audio, language, and embeddings — one API, pay-per-use, no servers to manage. Try every endpoint in the Playground before you write code.
5 modalities
Pay-per-use pricing
1 consistent API
Text-to-image and image-to-image models.
Text-to-video and image-to-video models.
Text-to-speech, speech-to-text, and voice models.
Open-source and hosted LLMs for chat & reasoning.
Vector embedding models for search and RAG.
Live status, metrics, and controls for all deployed serverless endpoints.
We’ve obsessively optimized every millisecond of container initialization.
